© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 31489
    Prev
    Next
    INDEX
    Explanations

    ^

    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
    aju
    -0.08
     Seoul
    -0.07
     correto
    -0.07
    正确
    -0.07
     �
    -0.07
    (Keys
    -0.07
     Celsius
    -0.07
     sneak
    -0.07
    停
    -0.07
     stealth
    -0.07
    POSITIVE LOGITS
     catholic
    0.09
     ballot
    0.09
     goût
    0.09
     Bernstein
    0.08
    香
    0.08
     آسیاب
    0.08
     konkurs
    0.08
     zend
    0.08
     અધ
    0.08
    Galer
    0.08
    Activations Density 0.007%

    No Known Activations