© 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. 19-RESID-POST-AA
    11. 20521
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    áculos
    -0.09
     finais
    -0.08
     ഡിസ
    -0.08
    在线观看视频
    -0.07
     multiplex
    -0.07
     atual
    -0.07
     inteira
    -0.07
     പുത
    -0.07
     zviri
    -0.07
     മുഴ
    -0.07
    POSITIVE LOGITS
    otl
    0.09
    кий
    0.09
    Quelques
    0.09
    few
    0.08
     einige
    0.08
    klad
    0.08
     few
    0.08
    %"),↵
    0.08
    ...(
    0.08
    "),
    0.08
    Activations Density 0.004%

    No Known Activations