© 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. 29728
    Prev
    Next
    INDEX
    Explanations

    rack

    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
     anne
    -0.08
     transcend
    -0.08
     Pale
    -0.07
     Reno
    -0.07
     mainstream
    -0.07
     ihr
    -0.07
     ebe
    -0.07
     theme
    -0.07
     Democratic
    -0.07
     Tons
    -0.07
    POSITIVE LOGITS
     Sparrow
    0.09
    绩
    0.08
    0.08
    uing
    0.07
    -mounted
    0.07
     improvis
    0.07
    cretion
    0.07
    -and
    0.07
    咪
    0.07
    Life
    0.07
    Activations Density 0.006%
    No Known Activations