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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 102165
    Prev
    Next
    INDEX
    Explanations

    A

    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
     the
    -0.13
    oue
    -0.09
    ability
    -0.09
    handeling
    -0.08
    :
    -0.08
    cluding
    -0.07
    หว่าง
    -0.07
     `
    -0.07
    the
    -0.07
    tractions
    -0.07
    POSITIVE LOGITS
    '=
    0.12
    '");↵
    0.11
    '";
↵
    0.11
    ’Im
    0.11
    '$
    0.10
    ′
    0.10
    ’，
    0.10
    !’
    0.10
    ’anno
    0.10
    '\
    0.10
    Activations Density 0.006%

    No Known Activations