© 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. 47374
    Prev
    Next
    INDEX
    Explanations

    Coding

    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
    Catalog
    -0.08
     extranj
    -0.08
     обмен
    -0.08
     estrange
    -0.08
     främ
    -0.08
    اڪ
    -0.08
     educativa
    -0.08
     parce
    -0.08
    ĩnh
    -0.08
     exchange
    -0.07
    POSITIVE LOGITS
     streams
    0.12
     Streams
    0.12
    Streams
    0.12
    streams
    0.11
    _stream
    0.10
     emits
    0.09
     stream
    0.09
    .stream
    0.09
    .Stream
    0.09
     поток
    0.09
    Activations Density 0.003%

    No Known Activations