© 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. 23-RESID-POST-AA
    11. 96233
    Prev
    Next
    INDEX
    Explanations

    French castles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    achement
    -0.09
     occurred
    -0.08
    (A
    -0.08
    :A
    -0.07
    unnan
    -0.07
    Occurrence
    -0.07
    __(
    -0.07
    stice
    -0.07
    __(↵
    -0.07
     occurs
    -0.07
    POSITIVE LOGITS
     Catarina
    0.08
    кид
    0.08
     klas
    0.08
     classifications
    0.08
     Mais
    0.08
     класси
    0.08
     Kens
    0.07
     feitos
    0.07
     Tracy
    0.07
     Diane
    0.07
    Activations Density 0.002%

    No Known Activations