Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11766
    Prev
    Next
    INDEX
    Explanations

    research/informative texts

    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
     అయ
    -0.08
    (?)
    -0.08
    有所
    -0.08
     illustri
    -0.08
    shoot
    -0.08
     Bryan
    -0.07
     fuertes
    -0.07
     ninete
    -0.07
     ఉంట
    -0.07
     ehd
    -0.07
    POSITIVE LOGITS
    ikan
    0.08
     obstante
    0.08
     Egypt
    0.08
     яка
    0.08
    .*;↵↵
    0.07
     infatti
    0.07
     witch
    0.07
     Egyptian
    0.07
     beispielsweise
    0.07
     viewed
    0.07
    Activations Density 0.319%

    No Known Activations