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. 76428
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    (\"
    -0.08
    Hum
    -0.08
     مواجهة
    -0.07
     это
    -0.07
     Molecular
    -0.07
     Infos
    -0.07
     ли
    -0.07
    Cred
    -0.07
    Questo
    -0.07
    -0.07
    POSITIVE LOGITS
    。この
    0.09
    。那么
    0.09
    。在
    0.09
    。我
    0.09
    。当
    0.09
    ,那么
    0.08
    。有
    0.08
    ,并
    0.08
     nước
    0.08
     impuesto
    0.08
    Activations Density 0.005%

    No Known Activations