© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 47980
    Prev
    Next
    INDEX
    Explanations

    的

    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
     تعريف
    -0.08
    向
    -0.08
     etwa
    -0.08
     لدى
    -0.08
    続きを
    -0.08
    正式
    -0.08
    urther
    -0.08
    continue
    -0.08
     bestimmten
    -0.08
     clairement
    -0.08
    POSITIVE LOGITS
    付
    0.17
    细
    0.16
    悉
    0.15
    細
    0.14
    默
    0.13
    耐
    0.12
    关
    0.12
     терп
    0.12
    用
    0.12
    辛
    0.12
    Activations Density 0.034%

    No Known Activations