© 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. 65588
    Prev
    Next
    INDEX
    Explanations

    education

    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
     xúc
    -0.08
    ivel
    -0.08
    ęs
    -0.07
     любви
    -0.07
    ersistent
    -0.07
    :a
    -0.07
    াদক
    -0.07
     kehidupan
    -0.07
    .Xr
    -0.07
    幸福
    -0.07
    POSITIVE LOGITS
     einzelne
    0.15
     individuele
    0.13
     individual
    0.13
     individuales
    0.12
    individual
    0.12
     einzel
    0.12
     individually
    0.12
     Individual
    0.11
     отдельных
    0.11
     pojed
    0.11
    Activations Density 0.065%

    No Known Activations