power-traces
gpt-oss-20b-moe-expert-power-traces-320k
GPT-OSS-20B MoE Expert Power Traces (320k, ChipWhisperer)
This dataset contains analog power traces captured with a ChipWhisperer Husky while running forced single-expert MoE computations derived from openai/gpt-oss-20b on an NVIDIA H100.
What is recorded
Each trace corresponds to one capture trial where:
A fixed expert id is selected (expert_00 ... expert_31).
A random hidden-state tensor is generated once per trial.
The selected expert computation is executed… See the full description on the dataset page: https://huggingface.co/datasets/masterpieceexternal/gpt-oss-20b-moe-expert-power-traces-320k.gpt-oss-20b-moe-expert-power-traces-320k-ds16k
GPT-OSS-20B MoE Expert Power Traces (Downsampled to 16k)
Downsampled variant of the 320k expert-trace capture set.
Source
Raw source dataset (same captures):
32 experts (expert_00..expert_31)
10,000 traces per expert
320,000 total traces
raw trace length ~195k samples per trace
Downsampling method
Each raw trace was resampled to exactly 16384 samples using linear interpolation (np.interp) matching the trainer resampling step.
No baseline normalization and no… See the full description on the dataset page: https://huggingface.co/datasets/masterpieceexternal/gpt-oss-20b-moe-expert-power-traces-320k-ds16k.h200-power-workload-traces-10MHz_5s
H200 GPU Power-Draw Workload Traces (10 MHz, 5 s)
Off-chip power side-channel recordings of an NVIDIA H200 NVL, captured with an
external current probe, for AI compute governance: determining
whether a GPU is training, running inference, or executing non-AI computation
from a signal that an external verifier could plausibly observe off-chip, and
how robust is detection to an operator who tries to disguise training as inference.
This is the dataset used for the paper Workload… See the full description on the dataset page: https://huggingface.co/datasets/simgar/h200-power-workload-traces-10MHz_5s.