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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130890
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     რომელ
    -0.14
     香港赛马会
    -0.12
     บริษัท
    -0.12
     จี
    -0.12
     Baebele
    -0.12
     իսկ
    -0.12
    երում
    -0.12
     דער
    -0.12
     fapaneng
    -0.12
     იგივე
    -0.12
    POSITIVE LOGITS
    x
    0.14
    a
    0.12
    two
    0.12
    g
    0.12
    both
    0.12
    b
    0.12
    *(
    0.12
    f
    0.12
    *
    0.12
    c
    0.11
    Activations Density 0.037%

    No Known Activations