© 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. 111414
    Prev
    Next
    INDEX
    Explanations

    diaper

    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
     Cine
    -0.10
    ie's
    -0.08
     aerospace
    -0.08
     vervol
    -0.08
     retorn
    -0.07
     casc
    -0.07
    ினிம
    -0.07
     protagonist
    -0.07
    erei
    -0.07
     individual's
    -0.07
    POSITIVE LOGITS
     diapers
    0.10
     diaper
    0.10
     dyed
    0.08
     worn
    0.08
    -fed
    0.08
     hose
    0.08
    bed
    0.08
     पहन
    0.08
    যোগ্য
    0.08
     hygiene
    0.07
    Activations Density 0.003%

    No Known Activations