© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44799
    Prev
    Next
    INDEX
    Explanations

    approximate

    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
    ті
    -0.08
    ткен
    -0.08
     дар
    -0.08
     দর্শ
    -0.08
     доказ
    -0.08
     ביז
    -0.08
    �
    -0.08
     설
    -0.08
     등장
    -0.08
     ұйымда
    -0.08
    POSITIVE LOGITS
     approx
    0.12
     approximate
    0.12
    approx
    0.12
     approximately
    0.11
     aproximadamente
    0.10
     yaklaşık
    0.10
     Approx
    0.10
     approximation
    0.10
    Approx
    0.10
     sekitar
    0.10
    Activations Density 0.026%

    No Known Activations