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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 60719
    Prev
    Next
    INDEX
    Explanations

    charging

    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
     turmoil
    -0.09
    骰
    -0.09
    Mailer
    -0.08
    メール
    -0.08
    Letters
    -0.08
    Suppress
    -0.08
    Username
    -0.08
    Email
    -0.08
    Correo
    -0.07
    Validation
    -0.07
    POSITIVE LOGITS
     roadside
    0.11
     aftermarket
    0.10
     инфраструкт
    0.09
    设施
    0.09
     ATP
    0.09
     स्थल
    0.08
     Betreiber
    0.08
     시설
    0.08
     infrastructure
    0.08
     outdoor
    0.08
    Activations Density 0.006%

    No Known Activations