© 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. 102494
    Prev
    Next
    INDEX
    Explanations

    import

    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
     for
    -0.09
     connecting
    -0.08
     of
    -0.08
     covering
    -0.08
     and
    -0.08
    connecting
    -0.08
     through
    -0.08
     representing
    -0.08
     in
    -0.07
    sending
    -0.07
    POSITIVE LOGITS
    ყვიტ
    0.11
     Callable
    0.11
     *↵↵
    0.11
    իռ
    0.11
     საუკეთ
    0.10
     *↵↵↵
    0.10
     чыгып
    0.10
    իոն
    0.10
     Iterable
    0.10
    ლე
    0.10
    Activations Density 0.000%

    No Known Activations