Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 61192
    Prev
    Next
    INDEX
    Explanations

    Word origins and latin

    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
     Dubai
    -0.08
    广州
    -0.08
     ಸೋಂಕ
    -0.08
     solusi
    -0.08
    新能源
    -0.07
     Сол
    -0.07
     sakit
    -0.07
     superconduct
    -0.07
     Kot
    -0.07
    สิ
    -0.07
    POSITIVE LOGITS
    gry
    0.09
    TACT
    0.08
    .def
    0.08
    entation
    0.08
    idea
    0.08
    ++)
    0.08
    edia
    0.08
    Fr
    0.08
    abr
    0.07
    tention
    0.07
    Activations Density 0.012%

    No Known Activations