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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 65415
    Prev
    Next
    INDEX
    Explanations

    documentation fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     გამო�
    -0.08
     ystä
    -0.08
    風
    -0.08
    Para
    -0.08
    Mesa
    -0.08
    ೇಟ
    -0.08
     teman
    -0.08
    աս
    -0.07
    Nesta
    -0.07
    率
    -0.07
    POSITIVE LOGITS
     acert
    0.07
     COMPLETE
    0.07
    _grp
    0.07
     Err
    0.07
     Autom
    0.07
     Transcript
    0.07
     absolute
    0.07
     intact
    0.07
     Diam
    0.07
     absolut
    0.07
    Activations Density 0.000%

    No Known Activations