© 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. 79015
    Prev
    Next
    INDEX
    Explanations

    Recipes

    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
     inso
    -0.08
    аки
    -0.08
     vint
    -0.08
     peaked
    -0.08
     ubiquitous
    -0.07
     yay
    -0.07
     occas
    -0.07
    ופו
    -0.07
    冷热
    -0.07
     analyses
    -0.07
    POSITIVE LOGITS
    _ag
    0.08
    _ff
    0.08
    બી
    0.08
     подряд
    0.07
    _pl
    0.07
    0.07
    SEL
    0.07
    res
    0.07
    ^\
    0.07
    /cm
    0.07
    Activations Density 0.050%

    No Known Activations