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. 74354
    Prev
    Next
    INDEX
    Explanations

    analysis writing style

    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
    词
    -0.09
     chronique
    -0.08
    ಿಣ
    -0.08
     cq
    -0.08
     пасля
    -0.08
    abla
    -0.08
    詞
    -0.08
     geple
    -0.08
    rowing
    -0.08
     favourable
    -0.07
    POSITIVE LOGITS
     Multiple
    0.08
    /base
    0.07
     Scal
    0.07
     All
    0.07
     Restaurants
    0.07
     thereof
    0.07
     Cherokee
    0.07
     Maint
    0.07
     Restaurant
    0.07
    ılar
    0.07
    Activations Density 0.000%

    No Known Activations