© 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. 77892
    Prev
    Next
    INDEX
    Explanations

    в

    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
     Steck
    -0.08
    ుత
    -0.07
    -0.07
     бар
    -0.07
     генерал
    -0.07
     Canton
    -0.07
    :^(
    -0.07
    ustri
    -0.07
     coaching
    -0.07
     benshi
    -0.07
    POSITIVE LOGITS
    .instant
    0.08
    ühle
    0.08
     gon
    0.08
     mê
    0.08
    Arizona
    0.08
    ثم
    0.08
    혼
    0.07
     Invoke
    0.07
    mages
    0.07
    -pound
    0.07
    Activations Density 0.000%
    No Known Activations