© 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. 75531
    Prev
    Next
    INDEX
    Explanations

    no

    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
    ád
    -0.08
    ಕ್�
    -0.08
     �
    -0.08
    _notify
    -0.08
    .invalidate
    -0.07
    _NOTIFY
    -0.07
    .notify
    -0.07
     кул
    -0.07
    אַנ
    -0.07
     meni
    -0.07
    POSITIVE LOGITS
    ，因为
    0.08
    ，要
    0.08
    या
    0.07
     क्योंकि
    0.07
    hnen
    0.07
    ience
    0.07
    SN
    0.07
    -oh
    0.07
    427
    0.07
    ，又
    0.07
    Activations Density 0.010%

    No Known Activations