© 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. 97411
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     рад
    -0.08
    log
    -0.07
     Groom
    -0.07
     clamp
    -0.07
     څخه
    -0.07
     кли
    -0.07
    жу
    -0.07
    ritel
    -0.07
     Sexual
    -0.07
     lur
    -0.07
    POSITIVE LOGITS
     integrity
    0.17
    integr
    0.15
    _integr
    0.14
    .integr
    0.14
     Integrity
    0.14
    -integr
    0.14
    Integrity
    0.13
    cross
    0.13
     crossorigin
    0.13
    .cross
    0.13
    Activations Density 0.003%

    No Known Activations