© 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. 19-RESID-POST-AA
    11. 103520
    Prev
    Next
    INDEX
    Explanations

    region

    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
    hairt
    -0.08
     قرآن
    -0.08
     ಪುಸ್ತಕ
    -0.08
     бүр
    -0.07
     نماز
    -0.07
     صلی
    -0.07
    -functions
    -0.07
     苹果手机
    -0.07
    beren
    -0.07
     werknemers
    -0.07
    POSITIVE LOGITS
    地区
    0.42
     പ്രദേശ
    0.40
     ప్రాంత
    0.39
     ಪ್ರದೇಶ
    0.38
     지역
    0.38
     વિસ્તારમાં
    0.37
    地域
    0.37
     regions
    0.37
     region
    0.37
    区域
    0.36
    Activations Density 0.167%

    No Known Activations