© 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. 63141
    Prev
    Next
    INDEX
    Explanations

    employee 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
     возраста
    -0.10
     слегка
    -0.08
    -hook
    -0.08
     возраст
    -0.08
    eleni
    -0.08
    ствен
    -0.08
     estadio
    -0.08
     возрасте
    -0.08
     LGPL
    -0.07
     hooking
    -0.07
    POSITIVE LOGITS
     rewarding
    0.13
    奖励
    0.12
     reward
    0.11
     rewarded
    0.11
     पुरस्कार
    0.11
     achie
    0.11
    优秀
    0.11
     récomp
    0.10
    reward
    0.10
     incentiv
    0.10
    Activations Density 0.016%

    No Known Activations