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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43936
    Prev
    Next
    INDEX
    Explanations

    banker's discounts problems

    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
     초기
    -0.08
     conscientious
    -0.07
    eders
    -0.07
     drv
    -0.07
    驾驶
    -0.07
     manuel
    -0.07
     إنه
    -0.07
     북
    -0.07
     conserve
    -0.07
     recount
    -0.07
    POSITIVE LOGITS
     plazo
    0.10
     prazo
    0.09
     pagamento
    0.09
     Zahlungs
    0.08
     pembayaran
    0.08
    金融
    0.08
     Serum
    0.08
     délai
    0.08
     delayed
    0.08
    (delay
    0.08
    Activations Density 0.011%

    No Known Activations