© 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. 23-RESID-POST-AA
    11. 6310
    Prev
    Next
    INDEX
    Explanations

    Korean particle 을/를

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     தெரிய
    -0.08
    整理
    -0.08
     veranderen
    -0.08
    ====
    -0.08
     വ്യക്തമാക്കി
    -0.08
     veranderd
    -0.08
     වෙන
    -0.07
     découvrez
    -0.07
     clarify
    -0.07
    elles
    -0.07
    POSITIVE LOGITS
     가진
    0.19
     가지고
    0.18
     가지
    0.18
     갖
    0.17
     ಹೊಂದ
    0.13
     내
    0.13
     கொண்ட
    0.13
     품
    0.12
     가져
    0.12
     지
    0.12
    Activations Density 0.003%

    No Known Activations