© 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. 65409
    Prev
    Next
    INDEX
    Explanations

    mental clarity and focus

    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
     gall
    -0.10
    -0.08
    (xml
    -0.08
    	xml
    -0.08
     Gaza
    -0.08
     annul
    -0.08
     Plumbing
    -0.07
     piscine
    -0.07
    aae
    -0.07
     wund
    -0.07
    POSITIVE LOGITS
     clare
    0.12
     clarity
    0.12
     precision
    0.11
     claridad
    0.10
     precisão
    0.09
     sharpen
    0.09
     précision
    0.09
     helder
    0.09
     precisión
    0.09
    晰
    0.08
    Activations Density 0.019%
    No Known Activations