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. 58986
    Prev
    Next
    INDEX
    Explanations

    high energy physics

    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
     Quilt
    -0.09
     Уни
    -0.09
     SOAP
    -0.09
     quilt
    -0.08
    eel
    -0.08
     комитет
    -0.08
    (change
    -0.08
    _uuid
    -0.08
     Tiffany
    -0.08
     komo
    -0.08
    POSITIVE LOGITS
    ფ
    0.08
     produces
    0.08
    istus
    0.07
     تولید
    0.07
     سرمایه
    0.07
     crois
    0.07
     achieves
    0.07
     produks
    0.07
     LEG
    0.07
     Ï
    0.07
    Activations Density 0.001%

    No Known Activations