© 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. 52
    Prev
    Next
    INDEX
    Explanations

    for

    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
     заказать
    -0.08
     ग्ल
    -0.08
     заказа
    -0.07
     Gl
    -0.07
     использу
    -0.07
    mack
    -0.07
     заказ
    -0.07
    	gl
    -0.07
     glow
    -0.07
    র্ক
    -0.07
    POSITIVE LOGITS
    Wal
    0.08
    (&:
    0.08
    (dic
    0.08
    ས
    0.07
     dž
    0.07
    Fem
    0.07
    .Sin
    0.07
    Detected
    0.07
    (sentence
    0.07
    ķ
    0.07
    Activations Density 0.046%

    No Known Activations