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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54595
    Prev
    Next
    INDEX
    Explanations

    holog

    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
     käyttä
    -0.08
     repertoire
    -0.08
     Capture
    -0.07
     ol
    -0.07
     naï
    -0.07
    )]↵↵
    -0.07
    .inverse
    -0.07
    রে
    -0.07
     intimacy
    -0.07
    ijks
    -0.07
    POSITIVE LOGITS
     teknologi
    0.09
     advertisements
    0.08
     matte
    0.08
     технологий
    0.08
     �
    0.08
     Nutz
    0.08
     paga
    0.08
     adverts
    0.08
    朋克
    0.07
    �
    0.07
    Activations Density 0.001%

    No Known Activations