© 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. 111000
    Prev
    Next
    INDEX
    Explanations

    formatting issues

    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
     өн
    -0.08
     Chesapeake
    -0.08
     ((*
    -0.08
    dealer
    -0.07
     Panamá
    -0.07
    庄
    -0.07
    教师
    -0.07
     карти
    -0.07
     encompasses
    -0.07
     распис
    -0.07
    POSITIVE LOGITS
     uninterrupted
    0.09
    \d
    0.09
     inert
    0.08
    Spacing
    0.08
    adrž
    0.08
     sublim
    0.08
    PREC
    0.08
    すす
    0.08
     cysyll
    0.08
     unmarried
    0.08
    Activations Density 0.002%

    No Known Activations