© 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. 24570
    Prev
    Next
    INDEX
    Explanations

    de

    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
     Anders
    -0.08
    明显
    -0.08
    719
    -0.07
     balk
    -0.07
    drag
    -0.07
     Veränderungen
    -0.07
     ayudan
    -0.07
     Drag
    -0.07
    芽
    -0.07
     drag
    -0.07
    POSITIVE LOGITS
     خطة
    0.12
     പദ്ധ
    0.11
     યોજના
    0.11
    ที่จะ
    0.11
     плане
    0.11
     계획
    0.10
     plan
    0.10
     priorities
    0.09
     plans
    0.09
     strategies
    0.09
    Activations Density 0.054%

    No Known Activations