© 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. 47768
    Prev
    Next
    INDEX
    Explanations

    on

    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
     أمام
    -0.07
     കഴ
    -0.07
     провер
    -0.07
     окруж
    -0.07
     keessatti
    -0.07
    ств
    -0.07
     verifica
    -0.07
     erleich
    -0.07
    grees
    -0.07
     Speaker
    -0.07
    POSITIVE LOGITS
    账
    0.09
     winnings
    0.09
     fisheries
    0.09
     amt
    0.08
    金额
    0.08
     appreciation
    0.08
    _amt
    0.08
     Umsatz
    0.08
     devotion
    0.08
    额度
    0.08
    Activations Density 0.011%

    No Known Activations