© 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. 91373
    Prev
    Next
    INDEX
    Explanations

    coffee

    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
     pioneered
    -0.08
    ter
    -0.08
     kece
    -0.08
     deput
    -0.07
    Kir
    -0.07
    ikh
    -0.07
     overhaul
    -0.07
    sv
    -0.07
    Builder
    -0.07
    Mario
    -0.07
    POSITIVE LOGITS
    味
    0.09
    бель
    0.09
     scent
    0.09
     запах
    0.08
     tendre
    0.08
     Herbal
    0.08
     ọdị
    0.08
     smell
    0.08
     аромат
    0.08
     geur
    0.08
    Activations Density 0.003%

    No Known Activations