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. 43820
    Prev
    Next
    INDEX
    Explanations

    exactly

    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
     누구
    -0.08
    ที่จะ
    -0.08
    ailed
    -0.08
    cups
    -0.07
    മ
    -0.07
    gehend
    -0.07
    .Any
    -0.07
    meni
    -0.07
     올
    -0.07
     rapidly
    -0.07
    POSITIVE LOGITS
     celebrate
    0.08
    -ish
    0.08
     تقريب
    0.08
     нест
    0.08
    онаи
    0.08
    طوان
    0.08
     Celebrate
    0.07
     commemorate
    0.07
    approximately
    0.07
     birkaç
    0.07
    Activations Density 0.009%

    No Known Activations