© 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. 65575
    Prev
    Next
    INDEX
    Explanations

    engage

    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
     Cur
    -0.08
     cra
    -0.08
     cur
    -0.07
    flake
    -0.07
    LOGIN
    -0.07
     pano
    -0.07
    Cur
    -0.07
    .amazon
    -0.07
     �
    -0.07
     Fö
    -0.07
    POSITIVE LOGITS
     envers
    0.07
     بالله
    0.07
    �
    0.07
     ami
    0.07
    лич
    0.07
    佛
    0.07
    ments
    0.07
    กับ
    0.07
    يبة
    0.07
     stakeholders
    0.07
    Activations Density 0.018%

    No Known Activations