© 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. 64828
    Prev
    Next
    INDEX
    Explanations

    recognition

    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
    dsn
    -0.08
    Kaj
    -0.08
     Term
    -0.08
     vali
    -0.07
     Cycl
    -0.07
     constraint
    -0.07
     madura
    -0.07
    ()
    -0.07
     tany
    -0.07
     moya
    -0.07
    POSITIVE LOGITS
     पुरस्कार
    0.13
     récomp
    0.13
     rewarding
    0.13
    奖励
    0.12
     congrat
    0.12
     praise
    0.12
    .reward
    0.12
     celebrating
    0.12
    างวัล
    0.12
     reward
    0.12
    Activations Density 0.031%

    No Known Activations