© 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. 114149
    Prev
    Next
    INDEX
    Explanations

    reasoning and explanations

    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
     বেশ
    -0.08
    CAT
    -0.08
     whoever
    -0.08
     hopefully
    -0.08
    耐
    -0.08
     ઉપરાંત
    -0.08
     Whatever
    -0.08
     whatever
    -0.08
     Concord
    -0.08
     tjen
    -0.08
    POSITIVE LOGITS
    ？
    0.17
    ？↵↵
    0.17
    ？↵
    0.15
    ؟
    0.15
    ?↵
    0.15
    ?↵↵
    0.15
    ?</
    0.14
    ？”
    0.14
    ؟↵↵
    0.14
    ؟↵
    0.14
    Activations Density 0.293%

    No Known Activations