© 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. 79330
    Prev
    Next
    INDEX
    Explanations

    catheter

    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
    /compiler
    -0.10
     compiler
    -0.09
    compiler
    -0.09
    750
    -0.08
    fighter
    -0.08
     deten
    -0.08
     retaliation
    -0.08
    lhs
    -0.07
     lhs
    -0.07
     destacados
    -0.07
    POSITIVE LOGITS
     catheter
    0.11
    .Ch
    0.09
    .Interop
    0.08
     drains
    0.08
     инфек
    0.08
     septic
    0.08
     جار
    0.08
     hoses
    0.08
    .Application
    0.08
     inconvenience
    0.08
    Activations Density 0.002%

    No Known Activations