© 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. 26308
    Prev
    Next
    INDEX
    Explanations

    adaptive optics and turbulence

    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
     UML
    -0.09
     Diagram
    -0.08
     diagram
    -0.08
     merchandise
    -0.08
    .diagram
    -0.07
     절
    -0.07
    亞
    -0.07
     straightforward
    -0.07
     സാമ
    -0.07
     Merchandise
    -0.07
    POSITIVE LOGITS
     imperfections
    0.08
    实时
    0.08
     skjø
    0.08
     Echt
    0.08
     squeezing
    0.08
     inning
    0.08
     aberr
    0.08
    Connor
    0.08
     fluctu
    0.08
    Inspir
    0.08
    Activations Density 0.003%

    No Known Activations