© 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. 30152
    Prev
    Next
    INDEX
    Explanations

    access

    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
     Jul
    -0.08
     posl
    -0.08
     Shelley
    -0.08
     pocket
    -0.08
     kepada
    -0.08
    /context
    -0.07
     lay
    -0.07
     하면
    -0.07
     برابر
    -0.07
     खत
    -0.07
    POSITIVE LOGITS
     preferential
    0.08
    います
    0.08
    0.08
    的是
    0.08
     preferred
    0.07
    paro
    0.07
    Spanish
    0.07
    yle
    0.07
     utilizing
    0.07
     equilibrium
    0.07
    Activations Density 0.010%
    No Known Activations