© 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. 68217
    Prev
    Next
    INDEX
    Explanations

    Japanese tea ceremony

    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
     lur
    -0.08
     isu
    -0.08
    机场
    -0.07
     runaway
    -0.07
     sued
    -0.07
    ]/
    -0.07
    Index
    -0.07
     asteroid
    -0.07
     tents
    -0.07
    larının
    -0.07
    POSITIVE LOGITS
     ritual
    0.15
     rituals
    0.15
     enjoyment
    0.14
     наслаж
    0.13
     Ritual
    0.12
    享
    0.12
     gestes
    0.12
     savor
    0.12
     Genuss
    0.11
     удовольствие
    0.11
    Activations Density 0.056%

    No Known Activations