© 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. 64879
    Prev
    Next
    INDEX
    Explanations

    закона

    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
     جي
    -0.08
    却
    -0.07
    .sam
    -0.07
     المد
    -0.07
    inactive
    -0.07
    ची
    -0.07
    /register
    -0.07
    Rub
    -0.07
    rub
    -0.07
    .Volume
    -0.07
    POSITIVE LOGITS
     Host
    0.08
    	hide
    0.08
    Host
    0.07
     hosts
    0.07
    λει
    0.07
     blacks
    0.07
    ()}</
    0.07
    ("</
    0.07
    (Gtk
    0.07
    ("\\
    0.07
    Activations Density 0.000%

    No Known Activations