<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Syed Raza</title><description>Personal site of Syed Raza — Head of AI at 2OS. Writing on interpretable ML for regulated lending, generative AI in banking, and topology in physics.</description><link>https://syedraza.com/</link><language>en-us</language><item><title>Sparse Autoencoders Are the SR 11-7 Tool I Wish I&apos;d Had</title><link>https://syedraza.com/blog/hello-world/</link><guid isPermaLink="true">https://syedraza.com/blog/hello-world/</guid><description>How mechanistic interpretability tools turn opaque LLMs into auditable systems regulated banks can actually deploy under existing model risk frameworks.</description><pubDate>Fri, 08 May 2026 00:00:00 GMT</pubDate><category>interpretability</category><category>MRM</category><category>banking</category><author>syedraza.f@gmail.com</author></item></channel></rss>