© 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. 111339
    Prev
    Next
    INDEX
    Explanations

    =

    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
     yt
    -0.09
    ıs
    -0.08
     [{}
    -0.08
     [])
    -0.08
     ço
    -0.08
     limiter
    -0.08
     ism
    -0.08
     Goede
    -0.08
     cesse
    -0.07
    planner
    -0.07
    POSITIVE LOGITS
     രംഗ
    0.11
    秋
    0.08
     Szene
    0.08
     शैली
    0.08
    Backdrop
    0.08
    Portrait
    0.08
    Scene
    0.08
    胡
    0.08
     ilumin
    0.08
     сцен
    0.08
    Activations Density 0.006%

    No Known Activations