© 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. 11-RESID-POST-AA
    11. 54359
    Prev
    Next
    INDEX
    Explanations

    SDS

    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
    alele
    -0.08
    hom
    -0.08
    abl
    -0.08
     ಸಲ
    -0.08
    ಷ್ಟ
    -0.07
    amba
    -0.07
    _DR
    -0.07
    on
    -0.07
    ...
    -0.07
     hom
    -0.07
    POSITIVE LOGITS
     shocked
    0.08
     nähdä
    0.08
     overpower
    0.08
    .Binding
    0.08
     pung
    0.08
     overcome
    0.07
     brace
    0.07
    .reset
    0.07
     Paragraph
    0.07
     mata
    0.07
    Activations Density 0.001%

    No Known Activations