© 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. 95697
    Prev
    Next
    INDEX
    Explanations

    basic

    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
    ન
    -0.09
    aña
    -0.08
     hiatus
    -0.08
    નની
    -0.08
    œurs
    -0.08
     Stair
    -0.08
     frío
    -0.08
     Tul
    -0.08
    ränkt
    -0.08
    Queryable
    -0.08
    POSITIVE LOGITS
    /basic
    0.12
    तः
    0.10
    来说
    0.08
     pleasures
    0.08
     básicos
    0.08
     basics
    0.08
    设施
    0.08
     హె
    0.08
     ದ
    0.07
    事項
    0.07
    Activations Density 0.021%

    No Known Activations