© 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 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. 63891
    Prev
    Next
    INDEX
    Explanations

    floor and numbers

    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
     localized
    -0.09
     inequality
    -0.08
     indefinite
    -0.08
    localized
    -0.08
    ẩn
    -0.07
     роз
    -0.07
     lemma
    -0.07
    Localized
    -0.07
     signature
    -0.07
     sme
    -0.07
    POSITIVE LOGITS
     fibrosis
    0.09
     utbild
    0.08
     divisions
    0.08
     rheumatoid
    0.08
     Regierungs
    0.07
     Rehab
    0.07
    ঢ়
    0.07
     Harvey
    0.07
     hadden
    0.07
     umfang
    0.07
    Activations Density 0.001%

    No Known Activations