© 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. 26295
    Prev
    Next
    INDEX
    Explanations

    healthy eating

    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
    Player
    -0.08
    FFT
    -0.08
     المحكمة
    -0.08
    Viewer
    -0.08
    perts
    -0.08
     парень
    -0.08
     Newman
    -0.07
    Editor's
    -0.07
     summons
    -0.07
     auditions
    -0.07
    POSITIVE LOGITS
     nutrients
    0.11
     nutrientes
    0.11
     nutr
    0.10
     nutritious
    0.10
     nutrient
    0.10
     nutrition
    0.10
     Nutr
    0.09
     congen
    0.09
     richness
    0.08
    .lower
    0.08
    Activations Density 0.015%

    No Known Activations