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. 15-RESID-POST-AA
    6. 13
    Prev
    Next
    INDEX
    Explanations

    5

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ỏa
    -0.09
    NSIndex
    -0.08
    954
    -0.08
     interesting
    -0.07
    ��
    -0.07
     útil
    -0.07
     καλ
    -0.07
    ceries
    -0.07
     surgeries
    -0.07
     Christine
    -0.07
    POSITIVE LOGITS
    /oder
    0.09
     или
    0.08
    /System
    0.08
     또는
    0.08
    이라고
    0.08
     massive
    0.08
    ambu
    0.08
     "\
    0.08
     Massive
    0.07
    或者
    0.07
    Activations Density 0.003%

    No Known Activations