© 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. 110943
    Prev
    Next
    INDEX
    Explanations

    fishing

    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
     алх
    -0.08
    行政
    -0.08
     ഭരണ
    -0.08
     Administrator
    -0.08
     Rector
    -0.08
        	↵
    -0.08
     corridors
    -0.08
     روابط
    -0.08
     epistem
    -0.08
     административ
    -0.08
    POSITIVE LOGITS
     bait
    0.10
     Shimano
    0.09
     beads
    0.08
    技巧
    0.08
    .Seek
    0.08
     sympathy
    0.08
    undy
    0.08
     dyed
    0.08
     షూట
    0.08
     মাছ
    0.08
    Activations Density 0.019%

    No Known Activations