© 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. 70762
    Prev
    Next
    INDEX
    Explanations

    fanfiction crossovers

    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
     সংক
    -0.07
     pils
    -0.07
     piccolo
    -0.07
     Minn
    -0.07
     tightened
    -0.07
     Digi
    -0.07
     Tight
    -0.07
     WX
    -0.07
     Undo
    -0.07
    pan
    -0.07
    POSITIVE LOGITS
     recruiters
    0.09
     satell
    0.09
     recruiter
    0.09
     aliens
    0.08
     ores
    0.08
     sete
    0.08
     assh
    0.08
     Europas
    0.08
     monsters
    0.08
     alluring
    0.08
    Activations Density 0.004%

    No Known Activations