© 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. 29549
    Prev
    Next
    INDEX
    Explanations

    .com

    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
    Комментарии
    -0.08
    Secrets
    -0.07
     secrets
    -0.07
     Secrets
    -0.07
     myths
    -0.07
     bleeding
    -0.07
     ауд
    -0.07
     робот
    -0.07
    结构
    -0.07
    ظيم
    -0.07
    POSITIVE LOGITS
     lipstick
    0.09
     accepte
    0.09
    .gif
    0.09
    -shirt
    0.09
    houder
    0.08
    &T
    0.08
     hexadecimal
    0.08
     shaded
    0.08
     orange
    0.08
    :pointer
    0.08
    Activations Density 0.001%

    No Known Activations