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

    Neuronpedia

    Jacobian LensNEW
    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. 112396
    Prev
    Next
    INDEX
    Explanations

    ebra

    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
     lĩnh
    -0.08
     kampen
    -0.08
     شپ
    -0.07
    .onclick
    -0.07
     metaphor
    -0.07
    icem
    -0.07
    obsolete
    -0.07
    기간
    -0.07
     kämp
    -0.07
     forehead
    -0.07
    POSITIVE LOGITS
     загруз
    0.08
     uploads
    0.08
     Rosal
    0.08
    rela
    0.08
    ongs
    0.07
    portal
    0.07
     permalink
    0.07
     парков
    0.07
    .Rendering
    0.07
    .Spec
    0.07
    Activations Density 0.001%

    No Known Activations