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. 12839
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     Bericht
    -0.08
    장은
    -0.08
     eros
    -0.08
    琪
    -0.07
     berichten
    -0.07
     Teresa
    -0.07
     Tonight
    -0.07
     auf
    -0.07
     contents
    -0.07
     Wagen
    -0.07
    POSITIVE LOGITS
     যাতে
    0.09
     waɗ
    0.09
     որը
    0.09
     ώστε
    0.09
     যেন
    0.08
     بحيث
    0.08
     ktoré
    0.08
    中过
    0.08
     ועד
    0.08
    оу
    0.08
    Activations Density 0.095%

    No Known Activations