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. 113926
    Prev
    Next
    INDEX
    Explanations

    filename conventions

    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
    ्यक्ष
    -0.08
    ラス
    -0.08
    .cloudflare
    -0.07
     cuotas
    -0.07
     CURLOPT
    -0.07
     köz
    -0.07
     administrar
    -0.07
     infinite
    -0.07
    .unwrap
    -0.07
     Pier
    -0.07
    POSITIVE LOGITS
    YYYY
    0.10
    _'
    0.09
     (*.
    0.09
    .xlsx
    0.09
     '[
    0.09
     নামে
    0.09
     Documents
    0.09
    /YYYY
    0.08
     circa
    0.08
     בשם
    0.08
    Activations Density 0.019%

    No Known Activations