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. 111827
    Prev
    Next
    INDEX
    Explanations

    workout instructions

    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
     constituency
    -0.08
     સી
    -0.08
     tarpe
    -0.07
     UML
    -0.07
    ਨਾ
    -0.07
    ન
    -0.07
    Vertices
    -0.07
    Wikipedia
    -0.07
     hõ
    -0.07
    ociation
    -0.07
    POSITIVE LOGITS
     descans
    0.10
     Enjoy
    0.10
     descanso
    0.09
     отдых
    0.09
     repetir
    0.09
     throughout
    0.09
     gedurende
    0.09
    .motor
    0.09
     Throughout
    0.09
    每天
    0.09
    Activations Density 0.012%

    No Known Activations