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. 77449
    Prev
    Next
    INDEX
    Explanations

    Great Depression

    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
     الشكل
    -0.08
    自主
    -0.08
    结果
    -0.08
    AJOR
    -0.08
     spacious
    -0.08
    ুস
    -0.07
     pesto
    -0.07
     esclarecer
    -0.07
    াক্ষ
    -0.07
     Blender
    -0.07
    POSITIVE LOGITS
     Roosevelt
    0.11
     unemployment
    0.09
     woes
    0.09
     severely
    0.09
     Severe
    0.09
    -era
    0.09
     afflicted
    0.09
     wart
    0.09
     Federal
    0.09
     federal
    0.09
    Activations Density 0.015%

    No Known Activations