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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 60711
    Prev
    Next
    INDEX
    Explanations

    streak

    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
    hilfe
    -0.09
    _finalize
    -0.08
     societ
    -0.08
    cribed
    -0.08
    わ
    -0.08
     Roberto
    -0.08
    rectile
    -0.08
     deline
    -0.08
    dist
    -0.08
    net
    -0.08
    POSITIVE LOGITS
     streak
    0.11
     consecutive
    0.10
    奖
    0.10
    连续
    0.09
     unbeaten
    0.09
     uninterrupted
    0.09
     snowfall
    0.09
    累计
    0.08
     连
    0.08
     spark
    0.08
    Activations Density 0.012%

    No Known Activations