© 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. 11-RESID-POST-AA
    11. 70110
    Prev
    Next
    INDEX
    Explanations

    change

    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
     Litt
    -0.08
     Bloomington
    -0.07
     تصبح
    -0.07
     clav
    -0.07
     paran
    -0.07
     cuero
    -0.07
     adhesive
    -0.07
     Spart
    -0.07
     zl
    -0.07
     monna
    -0.07
    POSITIVE LOGITS
     mellitus
    0.09
    -related
    0.08
     perpetr
    0.08
     whirl
    0.08
     মোক
    0.08
     fueled
    0.07
     embodied
    0.07
     regulating
    0.07
     Amph
    0.07
    -powered
    0.07
    Activations Density 0.006%

    No Known Activations