© 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. 54478
    Prev
    Next
    INDEX
    Explanations

    Code and variable declaration

    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
     gravitational
    -0.08
     nawo
    -0.08
     photographs
    -0.08
     закон
    -0.07
     тү
    -0.07
    GBT
    -0.07
    يي
    -0.07
     flora
    -0.07
     coax
    -0.07
    rechten
    -0.07
    POSITIVE LOGITS
     initialized
    0.14
    initialized
    0.13
     Initialized
    0.11
     состояния
    0.11
     variables
    0.10
     tracking
    0.10
     변수
    0.10
    variables
    0.10
     хран
    0.10
    _initialized
    0.10
    Activations Density 0.030%

    No Known Activations