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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102781
    Prev
    Next
    INDEX
    Explanations

    coffee

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ગામ
    -0.09
     céu
    -0.08
     cemetery
    -0.08
    住所
    -0.08
     paysages
    -0.08
     vacances
    -0.08
     probate
    -0.07
    家庭
    -0.07
     provincia
    -0.07
     знакомств
    -0.07
    POSITIVE LOGITS
     vending
    0.16
     dispenser
    0.14
     ماكينة
    0.13
     Automaten
    0.13
     автоматы
    0.13
     시스템
    0.13
    automater
    0.12
     سیستم
    0.12
     मशीन
    0.12
    系统
    0.12
    Activations Density 0.041%

    No Known Activations