© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70854
    Prev
    Next
    INDEX
    Explanations

    costs and budget

    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
     الأعلى
    -0.07
     grove
    -0.07
    仲
    -0.07
     क्र
    -0.07
    Ell
    -0.07
    크
    -0.07
     bowling
    -0.07
     potential
    -0.07
     invested
    -0.07
    _ITEM
    -0.07
    POSITIVE LOGITS
     Directions
    0.08
    emers
    0.08
    	ff
    0.08
     ditemukan
    0.08
    alleries
    0.08
    ooka
    0.08
    -dire
    0.08
     airlines
    0.08
     discovering
    0.07
     anon
    0.07
    Activations Density 0.013%

    No Known Activations