© 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. 54756
    Prev
    Next
    INDEX
    Explanations

    probabilistic graphical models

    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
     ssize
    -0.08
     plating
    -0.08
     épr
    -0.08
     clientèle
    -0.08
     carriage
    -0.08
     chez
    -0.08
     फेर
    -0.08
     courts
    -0.07
     ballistic
    -0.07
     hled
    -0.07
    POSITIVE LOGITS
     depicted
    0.09
    Diagram
    0.09
     diagram
    0.09
     depicts
    0.08
     Diagram
    0.08
     diagrams
    0.08
    diagram
    0.08
     depicting
    0.08
    dependencies
    0.08
    บุ
    0.08
    Activations Density 0.002%

    No Known Activations