© 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. 18001
    Prev
    Next
    INDEX
    Explanations

    User input in code

    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
     the
    -0.08
    ковые
    -0.08
     each
    -0.07
     semplice
    -0.07
    ásticos
    -0.07
    ")
    -0.07
    "
    -0.07
    ческие
    -0.07
    hoso
    -0.07
     fusion
    -0.07
    POSITIVE LOGITS
     =~
    0.13
    .chomp
    0.13
     /^
    0.10
     /^\
    0.10
    。↵↵
    0.10
    ،↵↵
    0.10
    .strip
    0.10
    აა
    0.10
    ။↵↵
    0.09
    ։↵↵
    0.09
    Activations Density 0.001%

    No Known Activations