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. 119987
    Prev
    Next
    INDEX
    Explanations

    OURCES

    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
    justify
    -0.08
    肉
    -0.08
    Seq
    -0.08
    يارات
    -0.07
    pty
    -0.07
    ppen
    -0.07
    ارية
    -0.07
    Onze
    -0.07
     dynasty
    -0.07
     practicality
    -0.07
    POSITIVE LOGITS
     Resources
    0.09
     tools
    0.09
     resources
    0.09
     скачать
    0.09
     ресурсов
    0.09
    网址
    0.09
     учеб
    0.08
     обуч
    0.08
     Download
    0.08
     datas
    0.08
    Activations Density 0.086%

    No Known Activations