© 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. 79012
    Prev
    Next
    INDEX
    Explanations

    direction

    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
     aconsel
    -0.08
    istemas
    -0.08
    ivan
    -0.08
     꾸
    -0.07
     cottage
    -0.07
    dan
    -0.07
     overtu
    -0.07
    ters
    -0.07
    <N
    -0.07
     Jie
    -0.07
    POSITIVE LOGITS
    ைப்பட
    0.08
    บน
    0.08
    ில்லை
    0.08
     считать
    0.08
    தாக
    0.08
    เป็น
    0.07
     olan
    0.07
    ட
    0.07
     onto
    0.07
    ைத்து
    0.07
    Activations Density 0.016%

    No Known Activations