Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41968
    Prev
    Next
    INDEX
    Explanations

    Russian word for "year"

    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
    'était
    -0.08
     mehreren
    -0.08
     ==
    -0.07
     lorsqu
    -0.07
    jective
    -0.07
     naive
    -0.07
    bool
    -0.07
    ורה
    -0.07
     Angry
    -0.07
     Method
    -0.07
    POSITIVE LOGITS
     Protector
    0.09
     impending
    0.09
    _Final
    0.08
    /T
    0.08
     pessoais
    0.08
     finales
    0.08
     సందర్భంగా
    0.08
    Compra
    0.08
    杯
    0.08
     pensa
    0.08
    Activations Density 0.010%

    No Known Activations