SAEScientist-Bench
Explore score history ↗Evaluates AI agents performing sparse autoencoder feature interpretation on Gemma-2-9B-IT, measuring feature rank, activation separation, and steering ability across 20 tasks.
- Released
- 2026-09-08
- Institutions
- Chinese Academy of Sciences · Institute of Automation · University of Chinese Academy of Sciences
- Evaluates
- Agents & Tool Use, General AI, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
SAEScientist-Bench paper and code
No reported scores are on record for this benchmark yet.