© 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. 110262
    Prev
    Next
    INDEX
    Explanations

    Reagan

    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
     tale
    -0.09
     顺
    -0.08
     consigo
    -0.08
    。↵//
    -0.08
     聚
    -0.08
     Tale
    -0.08
     madr
    -0.08
     Haj
    -0.07
     请
    -0.07
     mats
    -0.07
    POSITIVE LOGITS
    Lbl
    0.09
    .exe
    0.08
    Interpreter
    0.08
    composer
    0.08
     interpreter
    0.08
     composer
    0.07
     Kot
    0.07
    marine
    0.07
     Smok
    0.07
     Atkins
    0.07
    Activations Density 0.008%

    No Known Activations