© 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 EvalsExportsAPI 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. 112556
    Prev
    Next
    INDEX
    Explanations

    Numbers in equations

    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
     fibr
    -0.10
     伟
    -0.08
    fang
    -0.08
     funnel
    -0.08
     carpeting
    -0.08
    伟
    -0.07
    zut
    -0.07
    anking
    -0.07
     follicles
    -0.07
     preferential
    -0.07
    POSITIVE LOGITS
    Subtract
    0.09
    --;↵↵
    0.08
     -=
    0.08
     잘
    0.08
    .subtract
    0.08
    subtract
    0.08
     продажи
    0.08
     разобраться
    0.08
     minus
    0.08
     тэр
    0.07
    Activations Density 0.033%

    No Known Activations