© 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. 583
    Prev
    Next
    INDEX
    Explanations

    images

    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
     wafer
    -0.08
     wears
    -0.08
     Fug
    -0.08
     wore
    -0.08
     Manor
    -0.08
    IFO
    -0.08
     established
    -0.08
     diligent
    -0.08
     Wear
    -0.08
     gə
    -0.08
    POSITIVE LOGITS
     компози
    0.09
     illustrations
    0.08
     réaliser
    0.08
     depicting
    0.08
     primitives
    0.08
     professionally
    0.08
    -gener
    0.08
    ,text
    0.08
    /text
    0.07
     темат
    0.07
    Activations Density 0.003%

    No Known Activations