© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30101
    Prev
    Next
    INDEX
    Explanations

    divisors and factorization

    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
    ibody
    -0.08
     gekozen
    -0.08
     undergo
    -0.08
    ongodb
    -0.08
     مؤك
    -0.08
     olunur
    -0.08
     victime
    -0.08
    benzisa
    -0.08
     btc
    -0.07
    ราค
    -0.07
    POSITIVE LOGITS
    ，还
    0.08
    0.07
     яд
    0.07
    键
    0.07
     regulament
    0.07
     ones
    0.07
     Nevertheless
    0.07
    ，又
    0.07
     Kriterien
    0.07
     equivalents
    0.07
    Activations Density 0.020%
    No Known Activations