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. 7-RESID-POST-AA
    6. 1700
    Prev
    Next
    INDEX
    Explanations

    will produce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    是什么
    -0.08
    哪个
    -0.08
    有没有
    -0.08
     concorr
    -0.08
     айту
    -0.08
    тагы
    -0.08
    ,比如
    -0.08
     encycl
    -0.08
    _CHILD
    -0.07
    孩子
    -0.07
    POSITIVE LOGITS
     છું
    0.08
    rage
    0.08
     пок
    0.08
     passionately
    0.08
     tons
    0.08
     ans
    0.07
    toc
    0.07
    firm
    0.07
     예정
    0.07
     hates
    0.07
    Activations Density 0.037%

    No Known Activations