© 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. 108240
    Prev
    Next
    INDEX
    Explanations

    年

    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
     Å
    -0.08
    וות
    -0.08
     ved
    -0.08
     caution
    -0.08
     -*-
    -0.07
     longevity
    -0.07
     suerte
    -0.07
    BUT
    -0.07
    -0.07
     Eg
    -0.07
    POSITIVE LOGITS
     embal
    0.09
    概
    0.08
    .Collections
    0.08
     raz
    0.08
     ব্য
    0.08
    ke
    0.07
    ంద
    0.07
    Marketplace
    0.07
    ంది
    0.07
     rod
    0.07
    Activations Density 0.082%

    No Known Activations