Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129988
    Prev
    Next
    INDEX
    Explanations

    in

    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
    Sell
    -0.08
    aita
    -0.08
    discover
    -0.08
    Austin
    -0.07
     abrió
    -0.07
     Explore
    -0.07
     chercheurs
    -0.07
    Explore
    -0.07
    eline
    -0.07
    seau
    -0.07
    POSITIVE LOGITS
     accustomed
    0.16
     acostumbr
    0.13
     gewend
    0.13
    経験
    0.13
     привык
    0.12
     exposure
    0.12
    ustomed
    0.11
     gewohnt
    0.11
    习
    0.11
     ervaring
    0.11
    Activations Density 0.092%

    No Known Activations