© 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. 3-RESID-POST-AA
    11. 972
    Prev
    Next
    INDEX
    Explanations

    French and/or philosophy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jars
    -0.08
    -Le
    -0.08
    atı
    -0.08
     energía
    -0.07
     إليه
    -0.07
     UA
    -0.07
     nab
    -0.07
    -language
    -0.07
    Bog
    -0.07
     ję
    -0.07
    POSITIVE LOGITS
    zers
    0.08
    (id
    0.08
    idest
    0.08
    ("${
    0.08
    ово
    0.08
     compromising
    0.07
    овала
    0.07
     espectacular
    0.07
    med
    0.07
     Serien
    0.07
    Activations Density 0.001%

    No Known Activations