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. 113070
    Prev
    Next
    INDEX
    Explanations

    Bread dough preparation

    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
    _multi
    -0.08
     verv
    -0.08
     बह
    -0.08
     radi
    -0.07
    (Activity
    -0.07
     mór
    -0.07
     craz
    -0.07
    ystore
    -0.07
     spectator
    -0.07
    RNA
    -0.07
    POSITIVE LOGITS
     complain
    0.10
    漢
    0.08
     twijf
    0.08
     ignition
    0.07
     Perg
    0.07
    ாவ
    0.07
     hés
    0.07
    аха
    0.07
     anniversary
    0.07
     ambiance
    0.07
    Activations Density 0.000%

    No Known Activations