© 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. 23-RESID-POST-AA
    11. 6288
    Prev
    Next
    INDEX
    Explanations

    sipping

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    平方
    -0.09
    pseudo
    -0.08
     catast
    -0.08
    .Validator
    -0.08
    unchecked
    -0.08
     पट
    -0.07
    tm
    -0.07
    filesystem
    -0.07
     Polícia
    -0.07
     Carvalho
    -0.07
    POSITIVE LOGITS
     напит
    0.19
     drinks
    0.19
     sipping
    0.19
     drink
    0.18
     beverage
    0.17
     boissons
    0.17
    饮
    0.17
     coffee
    0.17
    喝
    0.17
    Drink
    0.17
    Activations Density 0.007%

    No Known Activations