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

    Neuronpedia

    Jacobian LensNEW
    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. 112507
    Prev
    Next
    INDEX
    Explanations

    database and licensing

    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
     Zinc
    -0.09
     Discount
    -0.09
     Zn
    -0.09
     girlfriend
    -0.08
     recursion
    -0.08
     Maths
    -0.08
     Compra
    -0.08
     Disability
    -0.08
     Kl
    -0.08
     Scala
    -0.08
    POSITIVE LOGITS
     spokes
    0.08
     provisions
    0.08
     configurations
    0.08
     harvested
    0.08
    config
    0.08
    administrator
    0.08
     installations
    0.07
    installed
    0.07
    Deployment
    0.07
     tissues
    0.07
    Activations Density 0.006%

    No Known Activations