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. 60612
    Prev
    Next
    INDEX
    Explanations

    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
    важ
    -0.08
     протяжении
    -0.08
     Stoff
    -0.07
     شب
    -0.07
    授
    -0.07
    .degree
    -0.07
    ":"","
    -0.07
     storefront
    -0.07
    Drupal
    -0.07
     Laufe
    -0.07
    POSITIVE LOGITS
    ker
    0.09
     mille
    0.07
    \Event
    0.07
     flour
    0.07
     fucking
    0.07
    _INCREMENT
    0.07
     everything
    0.07
     breed
    0.07
     fuller
    0.07
    ert
    0.07
    Activations Density 0.021%

    No Known Activations