© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 110071
    Prev
    Next
    INDEX
    Explanations

    ?

    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
    Negative Logits
     rápidamente
    -0.08
     অবশ্য
    -0.08
     তাহলে
    -0.08
     ಅದು
    -0.08
     Wee
    -0.07
     Sit
    -0.07
    atid
    -0.07
    ">
↵
    -0.07
    -example
    -0.07
     সে
    -0.07
    POSITIVE LOGITS
     기타
    0.09
    이나
    0.09
     edits
    0.08
     وجه
    0.08
     nổi
    0.08
     holy
    0.08
     Holly
    0.08
     meditation
    0.08
    하거나
    0.08
     �
    0.08
    Activations Density 0.074%

    No Known Activations