© 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. 11-RESID-POST-AA
    11. 113770
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Canberra
    -0.10
    Doctrine
    -0.09
     خدا
    -0.09
     sombra
    -0.09
     Doctrine
    -0.09
     graphite
    -0.09
    ldap
    -0.09
    .netbeans
    -0.08
     Ili
    -0.08
     ldap
    -0.08
    POSITIVE LOGITS
     वायरल
    0.14
    点赞
    0.14
     Tik
    0.11
    视频
    0.11
     trendy
    0.11
     catchy
    0.11
    Tik
    0.10
     वीडियो
    0.10
     hashtags
    0.10
     reels
    0.10
    Activations Density 0.033%

    No Known Activations