© 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. 79039
    Prev
    Next
    INDEX
    Explanations

    and

    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
     proprietary
    -0.08
     blond
    -0.08
     https
    -0.07
     �
    -0.07
    https
    -0.07
     reputable
    -0.07
     Foundation
    -0.07
    学历
    -0.07
     invented
    -0.07
     moll
    -0.07
    POSITIVE LOGITS
    进一步
    0.08
     Ï
    0.08
     subsequently
    0.08
    、更
    0.08
     дальней
    0.07
    _widgets
    0.07
    [result
    0.07
    最终
    0.07
     sooner
    0.07
    成交
    0.07
    Activations Density 37.975%

    No Known Activations