© 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. 78322
    Prev
    Next
    INDEX
    Explanations

    negations and uncertainty

    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
    тип
    -0.09
     Dieser
    -0.08
     четыр
    -0.08
     Trib
    -0.08
    дя
    -0.08
     cuarto
    -0.08
     époque
    -0.08
    牢记
    -0.08
     đô
    -0.08
     चार
    -0.08
    POSITIVE LOGITS
     inherently
    0.09
     lett
    0.08
     compared
    0.07
    Cmp
    0.07
    APP
    0.07
    +"\
    0.07
    POS
    0.07
    িন্ন
    0.07
     inherent
    0.07
    Therefore
    0.07
    Activations Density 0.183%

    No Known Activations