© 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 EvalsExportsAPI 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. 112572
    Prev
    Next
    INDEX
    Explanations

    trivial

    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
    翁
    -0.08
     zwar
    -0.08
     toilets
    -0.07
     corps
    -0.07
     sorgen
    -0.07
     harsh
    -0.07
     тав
    -0.07
    ergency
    -0.07
     cotton
    -0.07
     arbeiten
    -0.07
    POSITIVE LOGITS
     מאל
    0.09
     Paramount
    0.08
    leges
    0.08
     Nueva
    0.07
    .Gu
    0.07
     uchun
    0.07
     Мне
    0.07
     سوى
    0.07
    bate
    0.07
     Erd
    0.07
    Activations Density 0.010%

    No Known Activations