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. 90609
    Prev
    Next
    INDEX
    Explanations

    less than symbol

    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
     Jehovah
    -0.08
    .radio
    -0.08
     goose
    -0.07
     Ljubljana
    -0.07
     Hughes
    -0.07
     contabil
    -0.07
     Paying
    -0.07
     betalen
    -0.07
     Brits
    -0.07
     Гол
    -0.07
    POSITIVE LOGITS
     bounds
    0.08
     Bounds
    0.08
    ianza
    0.08
     acontecer
    0.07
    azen
    0.07
     acab
    0.07
     Bind
    0.07
    aturation
    0.07
     autos
    0.07
    XL
    0.07
    Activations Density 0.011%

    No Known Activations