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. 120327
    Prev
    Next
    INDEX
    Explanations

    mathematical computations

    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
     prescribing
    -0.09
    公开
    -0.08
     hành
    -0.08
     publicados
    -0.08
    发表
    -0.08
     willing
    -0.08
     gửi
    -0.08
     Delivered
    -0.08
     Teaching
    -0.08
     강조
    -0.08
    POSITIVE LOGITS
     sqrt
    0.16
    sqrt
    0.14
    .sqrt
    0.13
    .Sqrt
    0.11
    _squared
    0.11
     squared
    0.11
    Squared
    0.10
     √
    0.10
    √
    0.10
    qrt
    0.09
    Activations Density 0.033%

    No Known Activations