© 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. 64948
    Prev
    Next
    INDEX
    Explanations

    direction and movement

    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
     altar
    -0.08
     impreg
    -0.08
     hardcover
    -0.08
     edil
    -0.08
    Haus
    -0.08
    ోహ
    -0.08
    bildung
    -0.08
     hoogte
    -0.08
    asuring
    -0.08
    holt
    -0.08
    POSITIVE LOGITS
    _direction
    0.15
    Direction
    0.15
     direction
    0.14
    direction
    0.13
    .direction
    0.13
    方向
    0.13
     Direction
    0.13
    _DIRECTION
    0.12
     الاتجاه
    0.12
    (direction
    0.12
    Activations Density 0.014%

    No Known Activations