© 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. 95164
    Prev
    Next
    INDEX
    Explanations

    Russian language

    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
    ascii
    -0.08
    钱
    -0.08
    Jason
    -0.08
    quent
    -0.08
     Einstein
    -0.08
    ︎
    -0.08
    cheap
    -0.08
    mage
    -0.08
     boo
    -0.07
    sl
    -0.07
    POSITIVE LOGITS
     تكون
    0.10
     иметь
    0.10
     понадобится
    0.09
     אף
    0.08
     существенно
    0.08
    به
    0.08
     memb
    0.08
     Yin
    0.08
    �
    0.08
     tendrá
    0.08
    Activations Density 0.020%

    No Known Activations