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. 119251
    Prev
    Next
    INDEX
    Explanations

    sign-in instructions

    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
     Chim
    -0.09
     конструкции
    -0.08
    الغ
    -0.08
     बाब
    -0.07
     Yorkers
    -0.07
     کاربرد
    -0.07
     النهاية
    -0.07
    _Table
    -0.07
    yria
    -0.07
    arrison
    -0.07
    POSITIVE LOGITS
     खात
    0.10
     ખાત
    0.09
    账户
    0.09
    帐
    0.09
    航空
    0.09
     аккаун
    0.09
     federal
    0.08
     longtime
    0.08
    Subscribed
    0.08
    _accounts
    0.08
    Activations Density 0.015%

    No Known Activations