© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70325
    Prev
    Next
    INDEX
    Explanations

    Academic writing/citations

    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
     Hulk
    -0.08
    307
    -0.08
     Stadion
    -0.08
    chod
    -0.08
    旗下
    -0.07
    607
    -0.07
     protesting
    -0.07
     SBS
    -0.07
     DAG
    -0.07
    itus
    -0.07
    POSITIVE LOGITS
    Formatting
    0.09
     spacing
    0.08
    Sorting
    0.08
    Spacing
    0.08
    Authenticator
    0.08
     alphabetical
    0.08
    Ordering
    0.08
     formatting
    0.07
    -spacing
    0.07
    caler
    0.07
    Activations Density 0.007%

    No Known Activations