© 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. 129439
    Prev
    Next
    INDEX
    Explanations

    side

    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
     Ã
    -0.08
    -0.08
     ক্ল
    -0.08
     ಕ್ಲ
    -0.08
     क्ल
    -0.08
    Ã
    -0.07
    .Cl
    -0.07
    Â
    -0.07
     Cl
    -0.07
     ક્લ
    -0.07
    POSITIVE LOGITS
     باعت
    0.08
     Bezir
    0.08
    Für
    0.08
    werke
    0.08
    φερ
    0.08
     britagem
    0.08
    orsche
    0.08
     યોજ
    0.08
    ിയായ
    0.08
     suunn
    0.08
    Activations Density 0.000%
    No Known Activations