© 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. 114069
    Prev
    Next
    INDEX
    Explanations

    Phone

    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
     erled
    -0.10
     frequently
    -0.08
     Done
    -0.08
     permettant
    -0.08
     lenen
    -0.08
    >Description
    -0.08
     distant
    -0.08
     lend
    -0.07
     indispensable
    -0.07
     hoja
    -0.07
    POSITIVE LOGITS
     ста
    0.09
    .Rel
    0.08
     Sint
    0.08
    .Stream
    0.08
    生态
    0.08
     Ecos
    0.08
     Vig
    0.08
     перспектив
    0.07
     nou
    0.07
     stagn
    0.07
    Activations Density 0.007%

    No Known Activations