Ahson Saiyed
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1AI×1NLP×1Crypto×1
Frequent co-authors
Research Timeline
2026
Towards Understanding the Robustness of Sparse Autoencoders
The paper demonstrates that integrating Sparse Autoencoders (SAEs) into transformer residual streams significantly enhances the robustness of Large Language Models against various jailbreak attacks by reshaping the optimization geometry.
Highlighted terms show continued research focus across papers