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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 112991
    Prev
    Next
    INDEX
    Explanations

    8

    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
     Weber
    -0.09
    _PICK
    -0.08
    -0.08
    brook
    -0.08
    ö
    -0.08
    اول
    -0.07
     Nes
    -0.07
    üs
    -0.07
     ọgụ
    -0.07
    kunden
    -0.07
    POSITIVE LOGITS
     sle
    0.07
     velit
    0.07
    acters
    0.07
    ��
    0.07
    、有
    0.07
     revenir
    0.07
    scape
    0.07
    encode
    0.07
     ভূ
    0.07
     schn
    0.06
    Activations Density 0.002%

    No Known Activations