© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-RESID-POST-AA
    11. 1153
    Prev
    Next
    INDEX
    Explanations

    PI3K/AKT pathway

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suing
    -0.08
     Hiro
    -0.08
     HALF
    -0.08
     Honda
    -0.08
     Alum
    -0.08
     Ron
    -0.08
     вперед
    -0.08
     Valentine
    -0.07
     Hud
    -0.07
     Titan
    -0.07
    POSITIVE LOGITS
    🏼
    0.08
    partum
    0.07
    maint
    0.07
    ृत
    0.07
    -focused
    0.07
     emphas
    0.07
     macros
    0.07
     pé
    0.07
    aites
    0.07
    ív
    0.07
    Activations Density 0.000%

    No Known Activations