© 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. 108477
    Prev
    Next
    INDEX
    Explanations

    American Revolution

    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
    _train
    -0.09
    Train
    -0.08
    ()[
    -0.08
    ящ
    -0.08
     AV
    -0.08
     ट्रेन
    -0.08
     Train
    -0.08
     keb
    -0.08
     Sculpture
    -0.08
    train
    -0.07
    POSITIVE LOGITS
    财政
    0.09
     resentment
    0.09
     kepada
    0.08
     loyal
    0.08
     morale
    0.08
     heed
    0.08
    Fiscal
    0.08
     colonial
    0.08
     fiscal
    0.08
    ħ
    0.08
    Activations Density 0.013%

    No Known Activations