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. 106077
    Prev
    Next
    INDEX
    Explanations

    product models

    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
    用户名
    -0.09
    ා
    -0.09
     Uncle
    -0.09
    右翼
    -0.08
     protobuf
    -0.08
     THAN
    -0.08
     Provision
    -0.08
    笑
    -0.08
    첨
    -0.08
     Subs
    -0.08
    POSITIVE LOGITS
     Supreme
    0.08
     коль
    0.07
     kostenlos
    0.07
     सत
    0.07
     blue
    0.07
     everyday
    0.07
     விழ
    0.07
     cren
    0.07
     spl
    0.07
     infinity
    0.06
    Activations Density 0.030%

    No Known Activations