Project: https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/
This is a pruned variant of OpenAI's GPT-OSS-20B model, reduced to 14 experts per layer based on activation patterns from the AmanPriyanshu/GPT-OSS-20B MoE Expert Activations dataset. We analyzed router decisions across evaluation benchmarks to identify and retain experts most relevant for health or medicine tasks.
⚠️ Experimental Model: This is an experimental pruned model that may not work well - check the examples below to see if the outputs meet your needs before use.
This pruning approach reduces the model size while attempting to preserve performance on the target domain.
| Metric | Value |
|---|---|
| Base Model | openai/gpt-oss-20b |
| Architecture | Mixture-of-Experts Transformer |
| Total Parameters | ~10.2B (pruned from 21B) |
| Original Experts per Layer | 32 |
| Pruned Experts per Layer | 14 |
| Layers | 24 |
| Top-k Routing | 4 |
| Context Length | 128K tokens |
| Attention Heads | 64 (Query), 8 (Key-Value) |
| Residual Dimension | 2880 |
| Attention Pattern | Alternating dense & sliding window (128 tokens) |
| Positional Encoding | RoPE (Rotary Position Embedding) |
| Normalization | RMSNorm |
| Precision | BF16 |
| License | Apache 2.0 |
| Specialization | Health Or Medicine |
Mixture-of-Experts models contain multiple specialized sub-networks (experts) per layer. During inference, only a subset of experts are activated for each token. Expert pruning involves:
Note: Performance may vary depending on how well the pruned experts match your specific use case.
This medical domain model incorporates experts that activated highly during health and medical tasks from MMLU medical subjects. These experts specialize in clinical knowledge, anatomy, medical procedures, and health-related reasoning.
The expert selection process utilized our comprehensive analysis of router activation patterns across multiple evaluation benchmarks:
By identifying experts that consistently activated for health or medicine tasks, we created this specialized model that maintains domain expertise while significantly reducing computational requirements from 32 to 14 experts per layer.
This model is based on analysis from the GPT-OSS-20B MoE Expert Activations dataset available at: 🔗 https://huggingface.co/datasets/AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations
The dataset contains router activation patterns from OpenAI's GPT-OSS-20B model across diverse evaluation benchmarks, enabling the creation of these domain-optimized models through systematic expert pruning.
Our approach involves:
This is a direct pruning approach - no additional training was performed. The model inherits all capabilities from the original GPT-OSS-20B with focused expert selection.
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
# Load the specialized model on CPU
model = AutoModelForCausalLM.from_pretrained(
"AmanPriyanshu/gpt-oss-10.2b-specialized-health_or_medicine-pruned-moe-only-14-experts",
torch_dtype=torch.bfloat16,
device_map="cpu",
trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-10.2b-specialized-health_or_medicine-pruned-moe-only-14-experts")
# Generate with the model
messages = [
{"role": "user", "content": "What are the main functions of the human heart?"}
]
inputs = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt",
return_dict=True,
reasoning_effort="medium"
)
# Ensure inputs are on the same device as model
inputs = {k: v.to(model.device) for k, v in inputs.items()}
outputs = model.generate(
**inputs,
max_new_tokens=512,
do_sample=True,
temperature=0.1,
top_p=0.9,
pad_token_id=tokenizer.eos_token_id,
eos_token_id=tokenizer.eos_token_id
)
# Decode only the generated part
input_length = inputs['input_ids'].shape[1]
response_tokens = outputs[0][input_length:]
response = tokenizer.decode(response_tokens, skip_special_tokens=True)
print(response)
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
# Check MPS availability and load model
device = "mps" if torch.backends.mps.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
"AmanPriyanshu/gpt-oss-10.2b-specialized-health_or_medicine-pruned-moe-only-14-experts",
torch_dtype=torch.float16, # Better MPS compatibility
device_map=device,
trust_remote_code=True,
low_cpu_mem_usage=True
)
tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-10.2b-specialized-health_or_medicine-pruned-moe-only-14-experts")
# Generate with the model
messages = [
{"role": "user", "content": "What are the main functions of the human heart?"}
]
inputs = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt",
return_dict=True,
reasoning_effort="medium"
)
# Move inputs to model device
inputs = {k: v.to(model.device) if isinstance(v, torch.Tensor) else v for k, v in inputs.items()}
# Use torch.no_grad for MPS stability
with torch.no_grad():
outputs = model.generate(
**inputs,
max_new_tokens=512,
do_sample=True,
temperature=0.1,
top_p=0.9,
pad_token_id=tokenizer.eos_token_id,
eos_token_id=tokenizer.eos_token_id,
use_cache=True
)
# Decode only the generated part
input_length = inputs['input_ids'].shape[1]
response_tokens = outputs[0][input_length:]
response = tokenizer.decode(response_tokens, skip_special_tokens=True)
print(response)
For CUDA GPU inference, the models work with minimal modifications from the CPU example above. Simply change:
device_map="auto" # Will automatically use GPU if available
torch_dtype=torch.bfloat16 # or torch.float16
The following examples demonstrate the model's performance on health or medicine tasks:
Question: What are the main functions of the human heart?
Response:
<|channel|>analysis<|message|>Need to answer: pumping blood, regulating blood pressure, endocrine functions (atrial natriuretic peptide, renin), conduction system, valves, etc.<|end|><|start|>assistant<|channel|>final<|message|>**The human heart is a multi‑organ organ that performs several essential functions, all of which are tightly linked to the circulatory system. Below are the main roles of the heart, grouped into the most common categories:**
| **Primary Function** | **What it does** | **Key anatomical/physological features** |
|---|---|---|
| **P pumping blood** | Moves oxygen‑rich blood from the left side of the body (lungs, upper extremities) to the right side (heart, lower extremities) and then back to the lungs. | • 4 chambers (right atrium, left atrium, right ventricle, left ventricle) | • 3 valves (tricuspid, mitral, aortic) | • 3 valves (tricuspid, mitral, pulmonary) |
| **Regulating blood pressure** | Maintains a constant blood pressure by adjusting the force of contraction (stroke volume) and the resistance of the systemic circulation. | • Autonomic nervous system (sym‑/parasym) | • Hormonal systems (renin‑angiotensin, atrial natriuretic peptide) |
| **Endocrine (h endocrine) functions** | Releases hormones that influence fluid balance, blood volume, and vascular tone. | • Atrial natriuretic peptide (ANP) – vasodilator, natriuretic | • Renin – stimulates angiotensin‑II production |
| **Electrical conduction** | Generates the heartbeat and coordinates the contraction of the heart muscle. | • Sino‑atrial (SA) node – “pacemaker” | • Atrioventricular (AV) node – delays impulse to ventricles | • Bundle of His, Purkinje fibers – rapid conduction |
| **Mechanical support** | Provides a structural scaffold for the circulatory system, protecting blood vessels and organs. | • Coronary arteries – supply the heart itself | • Cardiac valves – prevent back‑flow |
| **Metabolic support** | Supplies the heart’s own energy needs and recycles metabolic waste. | • Coronary circulation – oxygen, nutrients | • Myocardial glycogen stores – energy reserve |
---
### 1. **P Pumping Blood**
- **Stroke Volume**: The amount of blood
Question: Explain the difference between bacteria and viruses.
Response:
<|channel|>analysis<|message|>Need explain differences: size, structure, replication, genetics, etc.<|end|><|start|>assistant<|channel|>final<|message|>**Bacteria vs. Viruses – The Key Differences**
| Feature | Bacteria | Viruses |
|---|---|---|
| **Definition** | Single‑cell, living organisms that can grow and divide | Non‑living particles that need a host cell to replicate |
| **Size** | 1–10 µm (micrometers) – visible under a light microscope | 0.1–100 nm (nanometers) – invisible to the naked eye |
| **Structure** | Complex cell with a cell wall, membrane, cytoplasm, ribosomes, DNA, and often organelles | Very simple: a protein shell (capsid) that enclues genetic material (DNA or RNA); no cytoplasmic machinery |
| **Genetic Material** | Usually a double‑stranded DNA genome (some bacteria have plasmids) | Can be DNA or RNA; may be single‑ or double‑stranded |
| **Replication** | Grow by cell division (mitosis‑like process) – can multiply rapidly (hours) | Must hij‑take a host cell’s machinery; replication can be very fast (minutes) but depends on host |
| **Energy Source** | Metabolic pathways (oxidation, photosynthesis, etc.) | None – relies on host cell’s energy |
| **Infection Mechanism** | Can colonize surfaces, invade tissues, or remain in the gut; may cause disease by toxins, enzymes, or immune response | Attach to a cell, enter it, release genome, replicate, and exit (lyse or exocytosis) |
| **Immune Response** | Recognized by pattern‑recognation receptors (PRRs) and adaptive immunity; can be cleared by antibiotics | Recognized by PRRs and adaptive immunity; cleared by antiviral drugs or immune‑mediated killing |
| **Treatment** | Antibiotics (target cell wall, protein synthesis, etc.) | Antivirals (target viral enzymes, replication steps) or vaccines |
| **Examples** | *Staphylococcus aureus*, *E. coli*, *Mycobacterium tuberculosis* | Influenza A, HIV, SARS‑CoV‑2, HPV |
**Key Take‑aways**
1. **Living vs. Non‑living** – Bacteria are living cells that can grow on their own; viruses are inert particles that need a host cell to replicate.
2
Question: What are the symptoms and causes of diabetes?
Response:
<|channel|>analysis<|message|>Need to explain symptoms and causes.<|end|><|start|>assistant<|channel|>final<|message|>**Diabetes mellitus** is a chronic metabolic disorder in which the body cannot produce or use insulin effectively, leading to high blood glucose levels. The two main types—Type 1 and Type 2—have overlapping symptoms but different underlying causes. Below is a concise overview of the symptoms and the causes for each type, plus a brief look at other forms of diabetes.
---
## 1. Symptoms of Diabetes
| Symptom | Why it happens | How it shows on the day |
|---|---|---|
| **Freckle‑like, sticky skin** | High glucose damages skin cells | Skin looks shiny, dry, or “sticky” |
| **Frequent thirst** | Kidneys try to excrete glucose | “I’m always thirsty” |
| **Frequent urination** | Kidneys excrete excess glucose | “I’m peeing a lot” |
| **Weight loss** (Type 1) | Body burns more glucose | Losing weight even without dieting |
| **Weight gain** (Type 2) | Insulin resistance → more fat stored | Gaining weight despite normal diet |
| **Fatigue / low energy** | Cells can’t use glucose efficiently | Feeling tired, sluggish |
| **Poor wound healing** | High glucose impairs immune & collagen | Cuts or sores take longer to close |
| **Vision changes** | High glucose damages retina | Blurred vision, floaters |
| **Increased infections** | Immune system weakened | Frequent colwors, thrush |
| **Night‑time hypoglycemia** (Type 1) | Insulin spikes too high | “I’m suddenly low‑glucose at night” |
| **Hyperglycemic episodes** (Type 2) | Blood glucose spikes | “I’m suddenly high‑glucose” |
> **Note** – Many people have no obvious symptoms early on, especially Type 2. That’s why routine screening is key.
---
## 2. Causes of Diabetes
### 2‑1. Type 1 Diabetes (T1D)
| Cause | Mechanism | Risk factors |
|---|---|---|
| **Auto‑immune destruction of β‑cells** | Immune system attacks insulin‑producing cells in the pancreas | Genetics, viral infections (e.g., enterovirus), early childhood, certain ethnic groups |
| **Genetic predisposition** | Certain HLA genes increase
If you use this model in your research, please cite:
@misc{priyanshu2025gptoss,
title={{GPT-OSS MoE Expert Fingerprinting: Analyzing Expert Activation Patterns in Mixture of Experts Models}},
author={Priyanshu, Aman and Vijay, Supriti},
year={2025},
howpublished={\url{https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/}},
note={Interactive analysis tool for expert activation patterns in MoE architectures}
}