© 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. 6317
    Prev
    Next
    INDEX
    Explanations

    想

    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
     Thoughts
    -0.09
     pensamentos
    -0.09
     pensamento
    -0.09
     hjälper
    -0.08
     pensamiento
    -0.08
     thinking
    -0.08
    vs
    -0.08
    веч
    -0.08
    Ident
    -0.08
    (parse
    -0.08
    POSITIVE LOGITS
    要
    0.35
     要
    0.26
    ，要
    0.24
     요
    0.16
    办法
    0.15
    요
    0.14
     to
    0.14
    让
    0.14
    象
    0.13
    我要
    0.13
    Activations Density 0.011%

    No Known Activations