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. 120158
    Prev
    Next
    INDEX
    Explanations

    calculating material costs

    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
     coexist
    -0.08
    unun
    -0.08
    สุด
    -0.08
    .Access
    -0.08
     നേത
    -0.08
    �
    -0.08
    .Try
    -0.08
    /history
    -0.08
    (Me
    -0.08
    _aff
    -0.08
    POSITIVE LOGITS
     perimeter
    0.13
     coverage
    0.13
     coverings
    0.11
    面积
    0.11
     покрытия
    0.11
     renovations
    0.11
     repaint
    0.11
     ремонт
    0.11
    施工
    0.11
     landscaping
    0.10
    Activations Density 0.035%

    No Known Activations