© 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. 7-RESID-POST-AA
    11. 773
    Prev
    Next
    INDEX
    Explanations

    ama

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Combat
    -0.09
     combat
    -0.09
    $title
    -0.08
    itelisted
    -0.08
     भूमिका
    -0.08
    ච
    -0.08
     concess
    -0.08
     ভূম
    -0.08
    Inspect
    -0.08
    (Editor
    -0.08
    POSITIVE LOGITS
    pro
    0.08
    百分
    0.08
     peur
    0.08
    _percent
    0.08
    比分
    0.08
     aufreg
    0.08
     suspicious
    0.08
     mole
    0.08
     NSNumber
    0.08
    _wire
    0.08
    Activations Density 0.001%

    No Known Activations