© 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. 31278
    Prev
    Next
    INDEX
    Explanations

    ator

    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
    charger
    -0.10
     чак
    -0.08
     વર્�
    -0.07
     charger
    -0.07
    YGON
    -0.07
     Partei
    -0.07
     Hampton
    -0.07
     chama
    -0.07
    ъл
    -0.07
    (argc
    -0.07
    POSITIVE LOGITS
     "\\
    0.09
    udal
    0.08
     provisional
    0.08
    ("\\
    0.07
     "../../../../
    0.07
     gods
    0.07
    ="//
    0.07
     ries
    0.07
     unforgettable
    0.07
    ಾರ್ಥ
    0.07
    Activations Density 0.000%

    No Known Activations