© 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 EvalsExportsinterp-engineNEWAPI 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. 63272
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     Пров
    -0.08
     chatter
    -0.07
     creeping
    -0.07
     whipping
    -0.07
     longa
    -0.07
    .conf
    -0.07
     sta
    -0.07
     тим
    -0.07
     chill
    -0.07
     controversy
    -0.07
    POSITIVE LOGITS
     vielmehr
    0.12
     बल्कि
    0.09
    っ
    0.08
     ahubwo
    0.08
    ека
    0.08
    SON
    0.08
    قام
    0.08
     بلکه
    0.08
    CDF
    0.08
     geg
    0.07
    Activations Density 0.032%

    No Known Activations