© 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. 79408
    Prev
    Next
    INDEX
    Explanations

    Blade Runner

    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
    (";
    -0.08
    忆
    -0.08
    .listdir
    -0.07
     aanwezig
    -0.07
     medios
    -0.07
    iest
    -0.07
    ධ්
    -0.07
    מד
    -0.07
     음
    -0.07
     Madre
    -0.07
    POSITIVE LOGITS
    0.10
    Practice
    0.08
     downtown
    0.08
    市
    0.08
     Revolution
    0.08
     SIM
    0.07
    Charge
    0.07
     Crédit
    0.07
     Practice
    0.07
     Charge
    0.07
    Activations Density 0.001%
    No Known Activations