© 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. 11-RESID-POST-AA
    11. 25002
    Prev
    Next
    INDEX
    Explanations

    and

    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
     voe
    -0.08
     pah
    -0.07
    utura
    -0.07
     Loyola
    -0.07
     AREA
    -0.07
     opr
    -0.07
     ida
    -0.07
     forgiveness
    -0.07
     iid
    -0.07
     uba
    -0.07
    POSITIVE LOGITS
    特色
    0.08
    .write
    0.08
    .splice
    0.08
    .Win
    0.08
    .theme
    0.07
     đa
    0.07
    �
    0.07
    Swing
    0.07
    .credentials
    0.07
    .sys
    0.07
    Activations Density 0.003%

    No Known Activations