© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 956
    Prev
    Next
    INDEX
    Explanations

    v

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     priv
    -0.09
     Jak
    -0.07
    EO
    -0.07
    าต
    -0.07
     çat
    -0.07
     Maks
    -0.07
     snabb
    -0.07
     tiga
    -0.07
     მოდ
    -0.07
    .U
    -0.07
    POSITIVE LOGITS
    $order
    0.08
    CHANNEL
    0.08
    [channel
    0.08
    -so
    0.08
     circumstance
    0.07
    $where
    0.07
    _Channel
    0.07
    ു
    0.07
    (channel
    0.07
    .vehicle
    0.07
    Activations Density 0.000%

    No Known Activations