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. 55412
    Prev
    Next
    INDEX
    Explanations

    "from now on" and foreign languages

    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
    -growing
    -0.08
    ದ್ದ
    -0.07
     falla
    -0.07
     undersø
    -0.07
    present
    -0.07
     ಇನ್ನ
    -0.07
    _present
    -0.07
    _ind
    -0.07
    grow
    -0.07
     falle
    -0.07
    POSITIVE LOGITS
     boyunca
    0.09
     vigilance
    0.09
    每天
    0.09
    äglich
    0.09
    只能
    0.08
    Calibri
    0.08
     天天
    0.08
     editions
    0.08
     jueves
    0.08
    觉得
    0.08
    Activations Density 0.022%

    No Known Activations