© 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. 6042
    Prev
    Next
    INDEX
    Explanations

    冲

    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
     PARA
    -0.09
     helps
    -0.08
    פאר
    -0.08
     praised
    -0.08
    фа
    -0.08
    寶
    -0.07
     parada
    -0.07
     praising
    -0.07
     melhora
    -0.07
    larni
    -0.07
    POSITIVE LOGITS
    击
    0.15
    擊
    0.13
     tekanan
    0.09
     pressures
    0.09
     restruct
    0.09
     uphe
    0.08
     pressure
    0.08
     bm
    0.08
    撃
    0.08
    压
    0.08
    Activations Density 0.003%

    No Known Activations