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. 42020
    Prev
    Next
    INDEX
    Explanations

    Mathematical and business calculations

    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
    ,自
    -0.09
     Superstar
    -0.08
    ’ac
    -0.08
     ਹੈ
    -0.07
     ndarray
    -0.07
     suprem
    -0.07
     מוב
    -0.07
    -0.07
     வழ
    -0.07
    Wikia
    -0.07
    POSITIVE LOGITS
    fighters
    0.08
    ırken
    0.08
    .bb
    0.07
    ээд
    0.07
    accion
    0.07
    --;↵↵
    0.07
    isser
    0.07
     बात
    0.07
     atentos
    0.07
    Contin
    0.07
    Activations Density 0.227%

    No Known Activations