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. 74762
    Prev
    Next
    INDEX
    Explanations

    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
     Tourism
    -0.09
    Honor
    -0.09
     honoring
    -0.09
    ópolis
    -0.09
     형태
    -0.09
     Aristotle
    -0.09
     작품
    -0.09
     Honors
    -0.09
     Children's
    -0.09
     honor
    -0.09
    POSITIVE LOGITS
     troubleshooting
    0.18
     troubleshoot
    0.14
    步骤
    0.14
    教程
    0.13
     Debian
    0.13
     procedures
    0.13
    _linux
    0.12
     Anleitung
    0.12
     steps
    0.12
     SSH
    0.12
    Activations Density 0.143%

    No Known Activations