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. 54037
    Prev
    Next
    INDEX
    Explanations

    common English language

    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
    rook
    -0.08
    -0.07
     Kräfte
    -0.07
    Dr
    -0.07
    Paren
    -0.07
     类
    -0.07
    reld
    -0.07
    Kil
    -0.07
    SECOND
    -0.07
    第二
    -0.07
    POSITIVE LOGITS
     многое
    0.09
     વગેરે
    0.09
    orra
    0.09
     vieles
    0.08
    等等
    0.08
     بالإضافة
    0.08
     आदि
    0.08
     mamm
    0.08
     എന്നിവ
    0.08
    ाँ
    0.08
    Activations Density 0.416%

    No Known Activations