© 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 EvalsExportsinterp-engineNEWAPI 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. 63109
    Prev
    Next
    INDEX
    Explanations

    case/bag

    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
     correlations
    -0.08
    Generally
    -0.08
     horizonte
    -0.08
    -heavy
    -0.08
     cumulative
    -0.07
     generally
    -0.07
     divergence
    -0.07
     obras
    -0.07
    227
    -0.07
    步
    -0.07
    POSITIVE LOGITS
    /frame
    0.09
     Deluxe
    0.09
     Tote
    0.09
     관리
    0.08
    .Memory
    0.08
     Agus
    0.08
     Edison
    0.08
    urry
    0.08
     Fancy
    0.08
    แม่
    0.08
    Activations Density 0.030%

    No Known Activations