© 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. 3-RESID-POST-AA
    11. 13123
    Prev
    Next
    INDEX
    Explanations

    -s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    263
    -0.08
    ्रा
    -0.08
     slo
    -0.07
     bk
    -0.07
    aq
    -0.07
    മെ
    -0.07
     Fahrzeuge
    -0.07
     patente
    -0.07
     Morgan
    -0.07
     ക്ര
    -0.07
    POSITIVE LOGITS
    issippi
    0.07
    loxacin
    0.07
    qrt
    0.07
    昨
    0.07
    -Gr
    0.07
    িয়ে
    0.07
     Oromo
    0.07
     مع
    0.07
    -Is
    0.07
    兄
    0.07
    Activations Density 0.006%

    No Known Activations