© 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. 3-RESID-POST-AA
    11. 13456
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PERFECT
    -0.07
    -0.07
     bases
    -0.07
     Secretary
    -0.07
    PLAN
    -0.07
    Planes
    -0.07
    力度
    -0.07
    坚持
    -0.07
    igning
    -0.07
    (Server
    -0.07
    POSITIVE LOGITS
     atend
    0.08
     furl
    0.08
    от
    0.08
    уляр
    0.08
     Owen
    0.08
     cab
    0.08
     leaps
    0.07
     Allen
    0.07
     trance
    0.07
    Allen
    0.07
    Activations Density 0.060%
    No Known Activations