© 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. 70679
    Prev
    Next
    INDEX
    Explanations

    Box

    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
     chế
    -0.08
    -cont
    -0.08
    .Feature
    -0.07
    עש
    -0.07
    破解
    -0.07
     ate
    -0.07
     carinho
    -0.07
     primul
    -0.07
    vit
    -0.07
     soin
    -0.07
    POSITIVE LOGITS
    supp
    0.08
    lookup
    0.08
     Perform
    0.08
     supplementary
    0.08
    __.'/
    0.07
     genealog
    0.07
     supple
    0.07
     episc
    0.07
    larini
    0.07
    ENTIAL
    0.07
    Activations Density 0.001%

    No Known Activations