© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110579
    Prev
    Next
    INDEX
    Explanations

    mathematical problem solving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /head
    -0.09
    (addr
    -0.09
    wenn
    -0.08
     Dependency
    -0.08
     tomo
    -0.08
    зен
    -0.08
     gär
    -0.08
    काश
    -0.08
    बाक
    -0.08
    मा
    -0.08
    POSITIVE LOGITS
     בד
    0.08
    ↵      ↵
    0.07
    喜
    0.07
    esthetic
    0.07
    0.07
     estética
    0.07
     ){↵↵
    0.06
    规定
    0.06
     ){↵
    0.06
    所谓
    0.06
    Activations Density 0.155%
    No Known Activations