© 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. 50746
    Prev
    Next
    INDEX
    Explanations

    up

    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
    院
    -0.08
    major
    -0.07
    (per
    -0.07
    COMP
    -0.07
     nasional
    -0.07
     fiquei
    -0.07
    (bb
    -0.07
    Бул
    -0.07
    Synopsis
    -0.07
    -0.07
    POSITIVE LOGITS
    レン
    0.08
    _es
    0.08
    ISCO
    0.08
    $json
    0.08
     rhe
    0.07
    'à
    0.07
    安县
    0.07
     गो
    0.07
     catastroph
    0.07
    -es
    0.07
    Activations Density 0.002%
    No Known Activations