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. 56112
    Prev
    Next
    INDEX
    Explanations

    painted

    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
    uild
    -0.09
    territ
    -0.08
    technical
    -0.08
    763
    -0.07
    tech
    -0.07
     svr
    -0.07
    486
    -0.07
     territories
    -0.07
    (fr
    -0.07
    chanical
    -0.07
    POSITIVE LOGITS
     Gary
    0.08
     Pharmaceutical
    0.08
    经理
    0.08
     makeup
    0.08
    三个
    0.08
     muffins
    0.08
     mango
    0.08
    辣
    0.08
     яб
    0.08
     നാല്
    0.08
    Activations Density 0.003%

    No Known Activations