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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 30340
    Prev
    Next
    INDEX
    Explanations

    skincare and moisturization

    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
     Palo
    -0.08
     chronological
    -0.08
    judge
    -0.07
    lex
    -0.07
     constructive
    -0.07
     purposeful
    -0.07
    按照
    -0.07
    282
    -0.07
    ipel
    -0.07
    Ì
    -0.07
    POSITIVE LOGITS
     воздуха
    0.09
     ця
    0.09
     humidity
    0.08
     moisture
    0.08
    ration
    0.08
     પાણી
    0.08
     wannan
    0.08
     воды
    0.08
     trao
    0.08
     nước
    0.08
    Activations Density 0.004%

    No Known Activations