© 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. 19-RESID-POST-AA
    11. 18384
    Prev
    Next
    INDEX
    Explanations

    Technical documentation

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    նակ
    -0.09
    ["+
    -0.08
    եկտ
    -0.08
     kollha
    -0.08
    րավ
    -0.08
     {}\
    -0.08
    րանք
    -0.07
    խ
    -0.07
    ubble
    -0.07
    կական
    -0.07
    POSITIVE LOGITS
     of
    0.11
    ibly
    0.08
    quently
    0.08
    $wp
    0.08
    irect
    0.07
    hetically
    0.07
    ently
    0.07
    (effect
    0.07
    arding
    0.07
    	of
    0.07
    Activations Density 0.182%

    No Known Activations