Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Ahson Saiyed

Ahson Saiyed

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

ML×1AI×1NLP×1Crypto×1

Frequent co-authors

Sabrina Sadiekh1×
Chirag Agarwal1×

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

Papers

cs.LGcs.AIcs.CLRecentApr 20, 2026

Towards Understanding the Robustness of Sparse Autoencoders

Ahson Saiyed, Sabrina Sadiekh, Chirag Agarwal

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…

View →