© 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. 68324
    Prev
    Next
    INDEX
    Explanations

    Armor

    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
    atan
    -0.09
     aromas
    -0.08
     gratuito
    -0.08
     liberdade
    -0.08
     GREAT
    -0.08
     gratuit
    -0.08
     libertad
    -0.08
    .tem
    -0.08
    ässer
    -0.08
     gratuitos
    -0.07
    POSITIVE LOGITS
     armor
    0.16
     protection
    0.14
     sturdy
    0.14
    Armor
    0.14
     resistente
    0.14
     Protection
    0.14
     Armor
    0.14
     protecting
    0.13
    Protection
    0.13
     armored
    0.13
    Activations Density 0.082%

    No Known Activations