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. 13044
    Prev
    Next
    INDEX
    Explanations

    the

    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
    وسي
    -0.08
    իւն
    -0.08
    հարկ
    -0.08
    าติ
    -0.08
    ហ
    -0.08
    liau
    -0.08
    တင္း
    -0.08
     пров
    -0.08
    უნდ
    -0.08
    եթե
    -0.08
    POSITIVE LOGITS
     Constraints
    0.08
    0.08
     Problem
    0.08
     constraints
    0.08
    措
    0.08
     parentheses
    0.07
     disclaim
    0.07
     estrict
    0.07
     gcd
    0.07
     Units
    0.07
    Activations Density 0.116%

    No Known Activations