© 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. 23-RESID-POST-AA
    11. 50598
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ака
    -0.08
    ژ
    -0.08
    hta
    -0.08
     Naar
    -0.08
    際
    -0.07
    арон
    -0.07
     aty
    -0.07
     hurting
    -0.07
    akings
    -0.07
    ег
    -0.07
    POSITIVE LOGITS
    (handle
    0.08
     obed
    0.08
    433
    0.08
    handle
    0.08
     handle
    0.08
    Handle
    0.07
    .handle
    0.07
    _XML
    0.07
     needed
    0.07
    432
    0.07
    Activations Density 0.007%

    No Known Activations