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. 111812
    Prev
    Next
    INDEX
    Explanations

    Kyoto

    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
     captcha
    -0.08
    insured
    -0.08
     parkeren
    -0.08
     verloren
    -0.07
     mater
    -0.07
     CAPTCHA
    -0.07
    -0.07
    oit
    -0.07
     career
    -0.07
     passport
    -0.07
    POSITIVE LOGITS
     Szene
    0.10
    descriptor
    0.09
    Minus
    0.08
    セット
    0.08
    厘
    0.08
     generosity
    0.08
    meniz
    0.08
    uff
    0.07
     sfr
    0.07
     handing
    0.07
    Activations Density 0.000%

    No Known Activations