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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 77350
    Prev
    Next
    INDEX
    Explanations

    function

    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
    geving
    -0.08
     quieras
    -0.08
    شط
    -0.08
    ulare
    -0.08
    (intent
    -0.08
    Collider
    -0.08
     ingestion
    -0.08
    American
    -0.08
    殖
    -0.07
    !!!↵
    -0.07
    POSITIVE LOGITS
     keynote
    0.08
    adl
    0.08
     META
    0.08
     pagination
    0.08
     performers
    0.07
    igl
    0.07
     titled
    0.07
    0.07
     knj
    0.07
     prer
    0.07
    Activations Density 0.002%

    No Known Activations