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. 12581
    Prev
    Next
    INDEX
    Explanations

    Chemical compositions

    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
    真人
    -0.08
    _CELL
    -0.07
    )!=
    -0.07
     pads
    -0.07
    tf
    -0.07
     reuse
    -0.07
    ))↵↵
    -0.07
    tv
    -0.07
     !==
    -0.07
     mange
    -0.07
    POSITIVE LOGITS
     модер
    0.09
     дым
    0.09
    Adds
    0.09
     VGA
    0.08
     roaming
    0.08
     additives
    0.08
     dioxide
    0.08
     Adds
    0.08
     添加
    0.08
     Drive
    0.08
    Activations Density 0.006%

    No Known Activations