© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 44293
    Prev
    Next
    INDEX
    Explanations

    role of

    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
     envy
    -0.09
    閱
    -0.08
     attempts
    -0.08
    υ
    -0.08
     હુમ
    -0.07
    (/*
    -0.07
     hide
    -0.07
     endeavors
    -0.07
     pursuits
    -0.07
    -на
    -0.07
    POSITIVE LOGITS
     निभ
    0.12
     played
    0.12
     jouent
    0.11
    作用
    0.10
     joué
    0.10
    发挥
    0.10
     gespeeld
    0.10
     role
    0.09
     spiller
    0.09
     भूमिका
    0.09
    Activations Density 0.053%

    No Known Activations