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. 131041
    Prev
    Next
    INDEX
    Explanations

    M

    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
    -photo
    -0.09
    .Photo
    -0.08
    iveness
    -0.08
    (Photo
    -0.08
     UPC
    -0.08
     fotografía
    -0.08
     photographic
    -0.08
     фотограф
    -0.08
    ности
    -0.08
    (photo
    -0.07
    POSITIVE LOGITS
    anti
    0.09
    'han
    0.09
    had
    0.08
    antiation
    0.08
    antt
    0.08
    477
    0.08
    IL
    0.08
    анта
    0.08
    embe
    0.07
    ಿ�
    0.07
    Activations Density 0.001%

    No Known Activations