© 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. 68131
    Prev
    Next
    INDEX
    Explanations

    independence

    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
     لها
    -0.09
    äte
    -0.08
    歓
    -0.08
     Umwelt
    -0.08
     व्यवहार
    -0.08
    ว่า
    -0.07
     importe
    -0.07
    -0.07
     चुनौती
    -0.07
    bae
    -0.07
    POSITIVE LOGITS
    licts
    0.07
    Starter
    0.07
     quarterback
    0.07
    Patrick
    0.07
    timer
    0.07
     partidos
    0.07
    球队
    0.07
     fucking
    0.07
    _sys
    0.07
     Patrick
    0.07
    Activations Density 0.002%
    No Known Activations