© 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. 110229
    Prev
    Next
    INDEX
    Explanations

    nesting/breeding

    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
     Оч
    -0.07
     memberships
    -0.07
    gbọ
    -0.07
     query
    -0.07
    sty
    -0.07
    roker
    -0.07
     thoughtfully
    -0.07
    egt
    -0.07
    igator
    -0.07
    Asc
    -0.07
    POSITIVE LOGITS
     SITE
    0.08
     HEL
    0.08
    	TEST
    0.08
     UTIL
    0.07
     ACP
    0.07
     NRA
    0.07
     ammonia
    0.07
     UNIT
    0.07
     UAV
    0.07
     STF
    0.07
    Activations Density 0.003%

    No Known Activations