© 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. 19-RESID-POST-AA
    11. 103470
    Prev
    Next
    INDEX
    Explanations

    say "32 or 64"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     multid
    -0.09
     dimensions
    -0.09
     dimensiones
    -0.09
     paced
    -0.08
     横
    -0.08
    _dimensions
    -0.08
    -dimensional
    -0.08
     dimension
    -0.08
     dimensión
    -0.08
     steady
    -0.08
    POSITIVE LOGITS
    .filters
    0.12
     filters
    0.12
    Filters
    0.12
    filters
    0.12
     Filters
    0.11
    (filters
    0.11
     filtros
    0.11
    _filters
    0.11
     आउट
    0.10
    过滤
    0.09
    Activations Density 0.001%

    No Known Activations