© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 20038
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     投稿
    -0.09
     Post
    -0.09
     estrogen
    -0.09
    Post
    -0.08
     Posts
    -0.08
    .Post
    -0.08
     pensez
    -0.08
    投稿
    -0.08
    $post
    -0.08
    -post
    -0.08
    POSITIVE LOGITS
     website
    0.22
    Website
    0.19
    website
    0.19
     Webseite
    0.19
     वेबसाइट
    0.18
    ウェ
    0.18
     Website
    0.18
     hjemmeside
    0.17
     websites
    0.17
    網站
    0.17
    Activations Density 0.053%

    No Known Activations