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. 11-RESID-POST-AA
    6. 11982
    Prev
    Next
    INDEX
    Explanations

    less than sign

    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
    (Base
    -0.08
    ('{
    -0.08
     gratuita
    -0.08
    _BASE
    -0.07
    camp
    -0.07
     iam
    -0.07
    &B
    -0.07
    ('&
    -0.07
    BMP
    -0.07
    \Data
    -0.07
    POSITIVE LOGITS
    :url
    0.09
    ாழ
    0.08
    同性
    0.08
    人民日报
    0.07
    ರಾದ
    0.07
     дұрыс
    0.07
     pervers
    0.07
     vetor
    0.07
    ]int
    0.07
    ordinates
    0.07
    Activations Density 0.033%

    No Known Activations