© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29427
    Prev
    Next
    INDEX
    Explanations

    suited

    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
     ખેડૂતો
    -0.09
     ბავშვ
    -0.08
     watoto
    -0.08
     ვიდეო
    -0.08
     livelihoods
    -0.08
     გავლ
    -0.08
     կենդ
    -0.08
     gifs
    -0.08
    يرات
    -0.08
     სპეცი
    -0.08
    POSITIVE LOGITS
    ś
    0.08
     sollen
    0.08
     стер
    0.08
    di
    0.07
    ularity
    0.07
     было
    0.07
     пришлось
    0.07
     termin
    0.07
    ethyl
    0.07
     бе
    0.07
    Activations Density 0.000%

    No Known Activations