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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 2612
    Prev
    Next
    INDEX
    Explanations

    statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    പുര
    -0.08
    一样
    -0.07
     advoc
    -0.07
     insurer
    -0.07
     dall
    -0.07
    博
    -0.07
    不用
    -0.07
    (prev
    -0.07
    (hr
    -0.07
    mär
    -0.07
    POSITIVE LOGITS
    latitude
    0.08
    Countdown
    0.08
    addon
    0.07
    ρυθ
    0.07
    Fake
    0.07
    _fake
    0.07
     Capit
    0.07
    Liste
    0.07
    utica
    0.07
    ugin
    0.07
    Activations Density 0.000%

    No Known Activations