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. 111791
    Prev
    Next
    INDEX
    Explanations

    period

    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
    াঙ
    -0.08
     tractors
    -0.08
     trapped
    -0.08
    界
    -0.07
     quest
    -0.07
     keypad
    -0.07
    _chart
    -0.07
    /calendar
    -0.07
     ringtone
    -0.07
     Alman
    -0.07
    POSITIVE LOGITS
     dropout
    0.13
    .dropout
    0.11
    _dropout
    0.10
     tasa
    0.09
    率
    0.09
    relu
    0.09
    .relu
    0.09
    (rate
    0.08
     taux
    0.08
     entropy
    0.08
    Activations Density 0.002%

    No Known Activations