© 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. 110920
    Prev
    Next
    INDEX
    Explanations

    R

    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
     verb
    -0.08
     preconce
    -0.08
    tle
    -0.08
    schaften
    -0.07
     gur
    -0.07
    ledge
    -0.07
     mime
    -0.07
    linger
    -0.07
     revis
    -0.07
     Levels
    -0.07
    POSITIVE LOGITS
    判
    0.10
     判
    0.09
    идер
    0.09
    unkulu
    0.09
    努
    0.08
     Ibn
    0.08
     모집
    0.08
    outil
    0.08
     실시
    0.08
    вел
    0.08
    Activations Density 0.008%

    No Known Activations