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. 109008
    Prev
    Next
    INDEX
    Explanations

    Legal/Official documents

    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
    赚钱
    -0.10
     Getting
    -0.10
     kids
    -0.09
     Yeah
    -0.09
     Surprisingly
    -0.09
     Definitely
    -0.09
     тоже
    -0.09
    看看
    -0.08
     newbies
    -0.08
     beginners
    -0.08
    POSITIVE LOGITS
     hereby
    0.19
     pursuant
    0.17
     herein
    0.14
     conformément
    0.13
    中华人民共和国
    0.13
     उक्त
    0.11
     memorandum
    0.11
     accordance
    0.11
    依法
    0.11
    しております
    0.10
    Activations Density 0.084%

    No Known Activations