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. 102827
    Prev
    Next
    INDEX
    Explanations

    research studies

    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
     seams
    -0.08
    omen
    -0.08
     seam
    -0.08
     making
    -0.08
     comfortably
    -0.07
     seamlessly
    -0.07
     befindet
    -0.07
     emerges
    -0.07
    making
    -0.07
     يك
    -0.07
    POSITIVE LOGITS
    alyzed
    0.09
     നടത്തിയ
    0.09
     showed
    0.09
     finalists
    0.09
     ನಡೆಸ
    0.09
     त्यांनी
    0.09
     videot
    0.09
     monitored
    0.08
     examined
    0.08
     examining
    0.08
    Activations Density 0.064%

    No Known Activations