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. 65214
    Prev
    Next
    INDEX
    Explanations

    coefficient

    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
    .ra
    -0.09
    腹
    -0.08
    ra
    -0.08
    SELF
    -0.08
    utex
    -0.08
    联合
    -0.07
     burning
    -0.07
    _ra
    -0.07
     upd
    -0.07
     ang
    -0.07
    POSITIVE LOGITS
     coefficient
    0.11
    Coefficient
    0.10
     коэффици
    0.10
     coefficients
    0.09
     coef
    0.09
    Coef
    0.09
     numerical
    0.08
     aparece
    0.08
     aparecem
    0.08
    आ
    0.08
    Activations Density 0.026%

    No Known Activations