© 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. 2921
    Prev
    Next
    INDEX
    Explanations

    를

    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
    ming
    -0.08
    other
    -0.08
     sustent
    -0.08
    ghi
    -0.07
     intensive
    -0.07
    ère
    -0.07
     việc
    -0.07
    нему
    -0.07
     ई
    -0.07
     fus
    -0.07
    POSITIVE LOGITS
     Cry
    0.08
     Ry
    0.08
     ill
    0.07
     knit
    0.07
     ind
    0.07
     вра
    0.07
     Troubles
    0.07
     dado
    0.07
    /_
    0.07
    rb
    0.07
    Activations Density 0.001%

    No Known Activations