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. 12841
    Prev
    Next
    INDEX
    Explanations

    Public/publicly

    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
     Wick
    -0.08
     Gob
    -0.08
     주민
    -0.08
     elétr
    -0.08
    NSObject
    -0.08
     נח
    -0.07
    новение
    -0.07
    URATION
    -0.07
     chauffage
    -0.07
    ixin
    -0.07
    POSITIVE LOGITS
     voorbeelden
    0.08
    いただ
    0.08
     record
    0.08
    trained
    0.08
    cone
    0.08
     recetas
    0.08
     گذا
    0.07
     recepten
    0.07
    Cone
    0.07
    ullo
    0.07
    Activations Density 0.017%

    No Known Activations