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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 55259
    Prev
    Next
    INDEX
    Explanations

    three

    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
    აო
    -0.09
    ாரம்
    -0.09
    ார
    -0.09
    ириш
    -0.09
    ално
    -0.08
    իր
    -0.08
    ავინ
    -0.08
    აობ
    -0.08
    арту
    -0.08
    ობდა
    -0.08
    POSITIVE LOGITS
     (
    0.09
     conjug
    0.07
     '
    0.06
    opu
    0.06
     antic
    0.06
     بالله
    0.06
    宋
    0.06
    874
    0.06
     relativ
    0.06
     "
    0.06
    Activations Density 0.568%

    No Known Activations