© 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. 108156
    Prev
    Next
    INDEX
    Explanations

    vernacular

    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
    etine
    -0.08
     bekl
    -0.07
    補
    -0.07
     את
    -0.07
     Lop
    -0.07
     birthdays
    -0.07
     комб
    -0.07
    حة
    -0.07
     добав
    -0.07
     Pil
    -0.07
    POSITIVE LOGITS
     língua
    0.10
     volk
    0.09
     idioma
    0.09
     langue
    0.09
     idiomas
    0.09
     langues
    0.09
    لغة
    0.09
     ભાષ
    0.09
     bahasa
    0.08
     ഭാഷ
    0.08
    Activations Density 0.010%

    No Known Activations