© 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. 7967
    Prev
    Next
    INDEX
    Explanations

    face

    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
    atisfied
    -0.08
    beste
    -0.08
    Lik
    -0.08
    Variation
    -0.08
     sát
    -0.08
     Расс
    -0.08
    Steam
    -0.08
    rence
    -0.07
     dependable
    -0.07
    ellite
    -0.07
    POSITIVE LOGITS
    anzu
    0.08
    oops
    0.07
     repositories
    0.07
     Dummy
    0.07
     atten
    0.07
     Transformers
    0.07
     stamina
    0.07
     notebooks
    0.07
     نشر
    0.07
     colabor
    0.07
    Activations Density 0.001%

    No Known Activations