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. 58867
    Prev
    Next
    INDEX
    Explanations

    what one needs

    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
    ypy
    -0.08
    频道
    -0.07
     accords
    -0.07
    osaic
    -0.07
     తర
    -0.07
     拉
    -0.07
    ाळ
    -0.07
     tổng
    -0.07
     ету
    -0.07
    vorming
    -0.07
    POSITIVE LOGITS
     лишь
    0.09
    মাত্র
    0.08
    GD
    0.08
     einzige
    0.08
     مجرد
    0.08
     Konzentr
    0.08
     Aval
    0.08
     Consum
    0.07
     vez
    0.07
    0.07
    Activations Density 0.026%

    No Known Activations