© 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. 111325
    Prev
    Next
    INDEX
    Explanations

    out

    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
     औ
    -0.08
     निर्म
    -0.08
     chem
    -0.08
     snem
    -0.08
     आप
    -0.07
     cello
    -0.07
     leider
    -0.07
     adag
    -0.07
    钢
    -0.07
     Passed
    -0.07
    POSITIVE LOGITS
    一下
    0.12
    看看
    0.12
     eens
    0.09
     внимательно
    0.09
     approfond
    0.09
    -see
    0.08
     menikmati
    0.08
     crít
    0.08
    ：https
    0.08
     visitar
    0.08
    Activations Density 0.051%

    No Known Activations