© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 50559
    Prev
    Next
    INDEX
    Explanations

    Marvel superheroes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sacramento
    -0.10
     classifieds
    -0.09
    彩票站
    -0.09
     DIG
    -0.09
     fertilizer
    -0.09
     моч
    -0.09
     �
    -0.09
     floppy
    -0.09
     Koop
    -0.09
     glazed
    -0.09
    POSITIVE LOGITS
     Avengers
    0.27
     Marvel
    0.26
    Marvel
    0.23
     Hulk
    0.21
     MCU
    0.19
     Wolverine
    0.18
     Loki
    0.17
     Thor
    0.17
     Tony
    0.16
     superhero
    0.16
    Activations Density 0.054%

    No Known Activations