Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 130326
    Prev
    Next
    INDEX
    Explanations

    plane

    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
    gui
    -0.08
    mapping
    -0.07
    (issue
    -0.07
    scar
    -0.07
    .view
    -0.07
     redistributed
    -0.07
    owment
    -0.07
     smile
    -0.07
     gamut
    -0.07
     Cá
    -0.07
    POSITIVE LOGITS
    .Direction
    0.09
    _DIRECTION
    0.09
     атмос
    0.08
     Inspirational
    0.08
     ther
    0.08
     نيو
    0.08
     напрям
    0.08
     duurzame
    0.08
     yog
    0.08
     Warfare
    0.08
    Activations Density 0.003%

    No Known Activations