© 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. 19-RESID-POST-AA
    11. 18060
    Prev
    Next
    INDEX
    Explanations

    Analytical reasoning

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
     lòt
    -0.10
    	then
    -0.10
    يضا
    -0.10
     ALSO
    -0.09
     altro
    -0.09
     hielt
    -0.09
     থেক
    -0.09
     Also
    -0.09
     akár
    -0.09
     it'll
    -0.09
    POSITIVE LOGITS
    :↵↵
    0.13
     некотор
    0.11
     some
    0.10
     given
    0.10
    某
    0.10
    ：↵↵
    0.10
     لدينا
    0.10
     seseorang
    0.09
     sebuah
    0.09
     máme
    0.09
    Activations Density 0.074%

    No Known Activations