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. 44041
    Prev
    Next
    INDEX
    Explanations

    Top

    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
     John
    -0.09
     Lamb
    -0.08
     Taylor
    -0.08
     丁
    -0.08
    _predict
    -0.08
     CSA
    -0.07
     Stein
    -0.07
     Clarkson
    -0.07
     fechado
    -0.07
     Verfügung
    -0.07
    POSITIVE LOGITS
    栏
    0.10
     toolbar
    0.09
    most
    0.08
    તમ
    0.08
    MOST
    0.08
     roba
    0.08
     bên
    0.08
    쪽
    0.07
    広告
    0.07
    頃
    0.07
    Activations Density 0.015%

    No Known Activations