© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 64731
    Prev
    Next
    INDEX
    Explanations

    Neural networks code

    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
     মূল
    -0.09
    原则
    -0.08
     desenvolver
    -0.08
    明确
    -0.08
    落实
    -0.08
    推进
    -0.08
    vilupp
    -0.08
    发展
    -0.08
     fomentar
    -0.08
     zoning
    -0.08
    POSITIVE LOGITS
     pretrained
    0.12
    =models
    0.09
     Models
    0.09
    ישהו
    0.09
     torchvision
    0.08
    _kwargs
    0.08
     blau
    0.08
     variants
    0.08
     Madeira
    0.08
    =False
    0.08
    Activations Density 0.003%

    No Known Activations