Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 61257
    Prev
    Next
    INDEX
    Explanations

    Threats and opportunities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whisky
    -0.08
     collapsed
    -0.08
     JOHN
    -0.08
    ך
    -0.08
     Cups
    -0.07
    ehova
    -0.07
     provas
    -0.07
     hairs
    -0.07
    intern
    -0.07
    aved
    -0.07
    POSITIVE LOGITS
     外
    0.10
    外
    0.09
    用于
    0.08
    External
    0.08
    这一
    0.08
     网络
    0.08
     获取
    0.08
     dış
    0.08
     외
    0.08
     external
    0.08
    Activations Density 0.002%

    No Known Activations