© 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. 23-RESID-POST-AA
    11. 49411
    Prev
    Next
    INDEX
    Explanations

    <<

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _tri
    -0.09
     требует
    -0.08
    alkan
    -0.08
    pras
    -0.08
    ază
    -0.08
     содержит
    -0.08
     claims
    -0.08
    apor
    -0.08
    achto
    -0.08
    ritra
    -0.08
    POSITIVE LOGITS
    EOF
    0.17
     EOF
    0.15
    EOS
    0.13
    END
    0.12
     eof
    0.11
     END
    0.11
     EOS
    0.11
    ENDO
    0.11
    -'
    0.11
    _END
    0.11
    Activations Density 0.001%

    No Known Activations