© 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. 79059
    Prev
    Next
    INDEX
    Explanations

    of

    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
    iency
    -0.08
     incertid
    -0.08
     Ideal
    -0.08
     Nyt
    -0.08
     mostly
    -0.08
     niso
    -0.07
     دوس
    -0.07
     Whole
    -0.07
    inais
    -0.07
    లేదు
    -0.07
    POSITIVE LOGITS
     dintre
    0.10
    叫
    0.09
    DV
    0.08
     dressed
    0.08
    qa
    0.08
    穿
    0.08
     גדול
    0.08
    重要
    0.08
    朋友
    0.08
    ka
    0.08
    Activations Density 0.054%

    No Known Activations