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. 46403
    Prev
    Next
    INDEX
    Explanations

    Widgets

    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
     uninter
    -0.08
    Wanted
    -0.08
     enum
    -0.07
    तर
    -0.07
     despre
    -0.07
    hol
    -0.07
    Smarty
    -0.07
     disper
    -0.07
     thơ
    -0.07
    百科
    -0.07
    POSITIVE LOGITS
    Previously
    0.08
     ഇതിന
    0.08
    0.07
     Creo
    0.07
    vection
    0.07
    登陆
    0.07
    创建
    0.07
     či
    0.07
     Wonderland
    0.07
     bagu
    0.07
    Activations Density 0.000%

    No Known Activations