© 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. 12926
    Prev
    Next
    INDEX
    Explanations

    remember

    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
     benchmarking
    -0.08
     benchmark
    -0.08
     Shay
    -0.07
    취
    -0.07
     gar
    -0.07
     Gar
    -0.07
     jeep
    -0.07
     Viet
    -0.07
     barred
    -0.07
    auto
    -0.07
    POSITIVE LOGITS
     Pir
    0.08
     lossis
    0.08
     duiz
    0.08
     beginnings
    0.07
     sensation
    0.07
    ictions
    0.07
     tood
    0.07
     Fool
    0.07
     sensations
    0.07
    اعات
    0.07
    Activations Density 0.028%

    No Known Activations