© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 258
    Prev
    Next
    INDEX
    Explanations

    parentheses

    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
    Not in Any Lists

    No Comments

    Negative Logits
     imedi
    -0.08
    bek
    -0.08
     immigration
    -0.08
    cri
    -0.08
     crack
    -0.08
    రకు
    -0.08
    (errno
    -0.08
    라이
    -0.07
    belief
    -0.07
     upr
    -0.07
    POSITIVE LOGITS
    .Ordinal
    0.09
     VN
    0.08
     Composer
    0.07
     ständig
    0.07
     abhängig
    0.07
    anut
    0.07
     cn
    0.07
     Phot
    0.07
    ач
    0.07
    _Play
    0.07
    Activations Density 0.001%

    No Known Activations