© 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. 11-RESID-POST-AA
    11. 47206
    Prev
    Next
    INDEX
    Explanations

    airline award redemptions

    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
    [min
    -0.08
     Kant
    -0.08
     Auditor
    -0.08
     Cupertino
    -0.07
     interdum
    -0.07
     cwd
    -0.07
     muh
    -0.07
     Seeder
    -0.07
    нь
    -0.07
     Oder
    -0.07
    POSITIVE LOGITS
    兑换
    0.12
    领取
    0.09
     redeemed
    0.08
     prizes
    0.08
    兑现
    0.08
     hadiah
    0.08
    领奖
    0.08
     신청
    0.08
     chickens
    0.08
    лист
    0.08
    Activations Density 0.025%

    No Known Activations