© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78019
    Prev
    Next
    INDEX
    Explanations

    buffering

    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
     anatomical
    -0.09
     anatomy
    -0.08
    multipart
    -0.08
     gern
    -0.08
     Ons
    -0.08
     perimeter
    -0.08
     postcard
    -0.08
     hallway
    -0.07
     cadas
    -0.07
    .like
    -0.07
    POSITIVE LOGITS
    buffer
    0.12
    _buffer
    0.12
     buffering
    0.12
    .buffer
    0.12
    Buffer
    0.12
    BUFFER
    0.11
     buffer
    0.11
    播放
    0.11
    _BUFFER
    0.11
    缓存
    0.11
    Activations Density 0.007%

    No Known Activations