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

    Neuronpedia

    APICircuit 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. 106329
    Prev
    Next
    INDEX
    Explanations

    ature

    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
     المرج
    -0.08
    contexts
    -0.08
     وضع
    -0.07
    ző
    -0.07
    шыя
    -0.07
     ezi
    -0.07
    ുമ
    -0.07
     //--------------------------------
    -0.07
     epsilon
    -0.07
    -0.07
    POSITIVE LOGITS
     চাক
    0.09
    兼职
    0.09
     candidature
    0.08
     Internship
    0.08
     overleden
    0.08
     नौकरी
    0.08
     unsolicited
    0.08
    帅
    0.08
     apprenticeship
    0.08
     unemployed
    0.08
    Activations Density 0.002%

    No Known Activations