© 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. 63842
    Prev
    Next
    INDEX
    Explanations

    uterus

    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
    rochen
    -0.09
    ore
    -0.08
    (predicate
    -0.08
    inspection
    -0.08
    itch
    -0.07
    (asset
    -0.07
     Punkte
    -0.07
     routinely
    -0.07
    orship
    -0.07
     طبق
    -0.07
    POSITIVE LOGITS
     슬
    0.08
     nay
    0.07
     aam
    0.07
     swing
    0.07
    ức
    0.07
     Won
    0.07
    305
    0.07
    119
    0.07
     Carl
    0.07
    �
    0.07
    Activations Density 0.001%

    No Known Activations