© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 43529
    Prev
    Next
    INDEX
    Explanations

    castles

    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
     vaping
    -0.10
    .Mapper
    -0.09
     plastik
    -0.09
     Prius
    -0.08
    .tolist
    -0.08
     Kunststoff
    -0.08
     menopause
    -0.08
    消费
    -0.08
     dishwasher
    -0.08
     dosage
    -0.08
    POSITIVE LOGITS
     castle
    0.17
     castles
    0.16
     fortress
    0.16
    Castle
    0.15
     Castle
    0.14
    castle
    0.13
     Fortress
    0.13
     रक्षा
    0.13
     defensive
    0.13
    堡
    0.12
    Activations Density 0.044%

    No Known Activations