© 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. 78503
    Prev
    Next
    INDEX
    Explanations

    Writing/Coding

    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
     GER
    -0.08
     çev
    -0.08
     Grace
    -0.08
     vejo
    -0.07
    -0.07
     intraven
    -0.07
     ympär
    -0.07
     Hall
    -0.07
     Abr
    -0.07
     compañero
    -0.07
    POSITIVE LOGITS
     manually
    0.15
     manual
    0.13
     tedious
    0.13
     вруч
    0.13
     cumbersome
    0.11
    Manual
    0.11
     Manual
    0.11
    .manual
    0.11
    manual
    0.11
     явно
    0.11
    Activations Density 0.023%
    No Known Activations