© 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. 44786
    Prev
    Next
    INDEX
    Explanations

    more

    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
     međ
    -0.08
     Interested
    -0.08
     quarterly
    -0.08
     арган
    -0.08
    Dod
    -0.08
    romo
    -0.08
     munsi
    -0.08
    insi
    -0.08
     institución
    -0.08
    ropical
    -0.08
    POSITIVE LOGITS
     বেশি
    0.10
     imbalance
    0.09
     ఎక్కువ
    0.09
     disparity
    0.09
     disproportion
    0.09
    略
    0.08
     sedikit
    0.08
     hervor
    0.08
     discrep
    0.08
     favored
    0.08
    Activations Density 0.009%

    No Known Activations