© 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. 64634
    Prev
    Next
    INDEX
    Explanations

    Food borders/edges

    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
     televis
    -0.09
    gaard
    -0.07
    klass
    -0.07
     occurs
    -0.07
    summ
    -0.07
     seedu
    -0.07
    oss
    -0.07
     If
    -0.07
     champagne
    -0.07
     Jahr
    -0.07
    POSITIVE LOGITS
     gebieden
    0.09
     areas
    0.08
    Borders
    0.08
     പ്രദേശ
    0.08
     områder
    0.08
     delimit
    0.08
    面积
    0.08
     Borders
    0.08
    Areas
    0.08
     regions
    0.08
    Activations Density 0.030%

    No Known Activations