Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 88257
    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
    ที่จะ
    -0.08
     toes
    -0.08
    chtig
    -0.08
    가는
    -0.08
     البيانات
    -0.08
     الكلام
    -0.08
     parms
    -0.07
     الكلمات
    -0.07
     /^[
    -0.07
     bolet
    -0.07
    POSITIVE LOGITS
     Mitchell
    0.08
     excellent
    0.08
     Blue
    0.08
     Paper
    0.07
     Khal
    0.07
     MH
    0.07
     Left
    0.07
     Ice
    0.07
     MIG
    0.07
     Van
    0.07
    Activations Density 0.145%

    No Known Activations