Skill UI

SAELens provides a framework for training and analyzing Sparse Autoencoders (SAEs). SAEs decompose the dense, often polysemantic activations of large language models into sparse, monosemantic features. Use this when you need to discover the discrete, interpretable concepts a model has learned, study feature superposition, or analyze specific safety-relevant behaviors (like bias or deception) within deep neural networks.

Implements Microsoft's Enhanced Security Admin Environment (ESAE) tiered administration model for Active Directory. This skill guides the hardening of AD privileged access architecture by establishing strict separation between Tier 0, Tier 1, and Tier 2 accounts. It is essential for mitigating advanced threats like pass-the-hash, Kerberoasting, and ensuring compliance with industry standards (NIST 800-53).

Covers WPA3/SAE attack techniques including transition-mode downgrade, Dragonblood side-channel analysis, SAE authentication flooding, H2E checks, and Wi-Fi 6E implications. Useful for assessing wireless security gaps and validating defensive hardening.