© 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. 95641
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
     ordeal
    -0.09
     solitaire
    -0.09
     Birthday
    -0.09
     birthdays
    -0.09
     acquaintances
    -0.09
     раздраж
    -0.09
     ocas
    -0.09
     manchmal
    -0.09
     Angry
    -0.09
     coworkers
    -0.09
    POSITIVE LOGITS
     추진
    0.18
    打造
    0.14
    政府
    0.14
    战略
    0.14
     sustainably
    0.13
    产业
    0.12
     visionary
    0.12
     impulsar
    0.12
     beneficiaries
    0.12
    习近平
    0.12
    Activations Density 0.032%

    No Known Activations