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. 111677
    Prev
    Next
    INDEX
    Explanations

    split

    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
     coax
    -0.08
    ීමට
    -0.08
     america
    -0.08
    705
    -0.08
    onaut
    -0.08
     sauf
    -0.08
     tastes
    -0.08
    ્વ
    -0.08
     mup
    -0.08
     ldc
    -0.08
    POSITIVE LOGITS
     tiers
    0.09
    categorized
    0.09
     categorized
    0.09
     Bereichen
    0.09
     ವಿಭಾಗ
    0.09
    如下
    0.09
     तीन
    0.08
     breaking
    0.08
     categories
    0.08
     Kategorien
    0.08
    Activations Density 0.022%

    No Known Activations