© 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. 108434
    Prev
    Next
    INDEX
    Explanations

    овать

    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
     هاتف
    -0.09
     gifted
    -0.07
     müs
    -0.07
     haddii
    -0.07
     diy
    -0.07
    +"]
    -0.07
    +",
    -0.07
     الهاتف
    -0.07
     hugs
    -0.07
    Gift
    -0.07
    POSITIVE LOGITS
    izwa
    0.08
    _nc
    0.08
     Rochester
    0.08
     coord
    0.08
    .coord
    0.08
     coords
    0.08
    काम
    0.08
     sanity
    0.08
     Canterbury
    0.07
    amat
    0.07
    Activations Density 0.000%

    No Known Activations