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. 55924
    Prev
    Next
    INDEX
    Explanations

    styling

    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
     acupuncture
    -0.09
     Reiki
    -0.08
     Years
    -0.08
     reimb
    -0.08
     Anthropology
    -0.07
    hei
    -0.07
    mpi
    -0.07
    -years
    -0.07
    anceled
    -0.07
     asio
    -0.07
    POSITIVE LOGITS
    \Facades
    0.11
     forecasting
    0.09
     توقع
    0.09
     דאָס
    0.09
     стаб
    0.09
     hierfür
    0.08
    יווי
    0.08
    -tooltip
    0.08
    יס
    0.08
     stadium
    0.08
    Activations Density 0.009%

    No Known Activations