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. 111970
    Prev
    Next
    INDEX
    Explanations

    Chinese text

    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
    -0.09
     pensioen
    -0.09
     Rollen
    -0.09
    рики
    -0.08
     escrow
    -0.08
     للب
    -0.08
     Iceland
    -0.08
     Upt
    -0.08
    али
    -0.08
     bleu
    -0.08
    POSITIVE LOGITS
    中国特色社会主义
    0.10
    习近平
    0.10
     Lenin
    0.10
    群众
    0.09
     prolet
    0.09
    马克
    0.09
     Aristotle
    0.09
     Marx
    0.09
     oppressed
    0.09
    共产党
    0.09
    Activations Density 0.012%

    No Known Activations