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. 65200
    Prev
    Next
    INDEX
    Explanations

    prompt

    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
     incompetent
    -0.08
    alyzed
    -0.08
    prot
    -0.07
    ඹ
    -0.07
    -0.07
     banal
    -0.07
    QUES
    -0.07
    =True
    -0.07
    .*?)
    -0.07
     bully
    -0.07
    POSITIVE LOGITS
     прямо
    0.10
     Kav
    0.08
    字符串
    0.08
     Diagn
    0.08
     Coc
    0.07
     manually
    0.07
     Facility
    0.07
     Feature
    0.07
     zusamm
    0.07
     dirett
    0.07
    Activations Density 0.012%

    No Known Activations