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. 77279
    Prev
    Next
    INDEX
    Explanations

    completion, end

    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
     Aurora
    -0.08
     Seeing
    -0.07
     možnosti
    -0.07
    ూర
    -0.07
     Capitals
    -0.07
     Πα
    -0.07
     пост
    -0.07
     cadre
    -0.07
     امکانات
    -0.07
    函
    -0.07
    POSITIVE LOGITS
    Qed
    0.08
     wrongdoing
    0.08
     vay
    0.08
    終了
    0.08
    aughty
    0.08
     pointless
    0.08
    .Exit
    0.08
     presumed
    0.08
    ুনি
    0.07
    undred
    0.07
    Activations Density 0.002%

    No Known Activations