© 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. 63899
    Prev
    Next
    INDEX
    Explanations

    bar

    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
     céré
    -0.08
     لمدة
    -0.08
     الحساب
    -0.08
    DTD
    -0.08
     resin
    -0.08
     الأح
    -0.08
     tør
    -0.08
     srand
    -0.08
    ిధ
    -0.08
     spores
    -0.08
    POSITIVE LOGITS
    .toolbar
    0.11
    (toolbar
    0.10
    toolbar
    0.10
     toolbar
    0.10
    _toolbar
    0.10
    -toolbar
    0.09
    Toolbar
    0.09
    _NAV
    0.09
    导航
    0.09
    :title
    0.09
    Activations Density 0.003%

    No Known Activations