© 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. 23-RESID-POST-AA
    11. 48136
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
     upholstered
    -0.08
     aden
    -0.07
    .sheet
    -0.07
     điện
    -0.07
    _EXT
    -0.07
    acific
    -0.07
    ADM
    -0.07
    TTY
    -0.07
     ann
    -0.07
    .curr
    -0.07
    POSITIVE LOGITS
     Trim
    0.08
    учу
    0.08
     dek
    0.08
     эн
    0.08
     قي
    0.08
     trims
    0.08
     Climate
    0.08
     ик
    0.08
    unzi
    0.08
     klima
    0.07
    Activations Density 0.001%

    No Known Activations