© 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. 102371
    Prev
    Next
    INDEX
    Explanations

    ular

    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
    ENCE
    -0.08
    oten
    -0.08
    .Graphics
    -0.08
    -elle
    -0.08
    ÷
    -0.08
    ியல்
    -0.07
     dedication
    -0.07
     dédiée
    -0.07
    ücke
    -0.07
     parand
    -0.07
    POSITIVE LOGITS
     CFDs
    0.08
    loaded
    0.08
     അവർ
    0.08
     baskets
    0.08
     Berm
    0.07
     പ്രമുഖ
    0.07
    groups
    0.07
     combos
    0.07
     mikið
    0.07
     대상으로
    0.07
    Activations Density 0.000%

    No Known Activations