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. 49235
    Prev
    Next
    INDEX
    Explanations

    Diacritics and typographical notation

    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
     Dennis
    -0.08
     binge
    -0.08
    teva
    -0.08
    -0.08
     consumption
    -0.07
    gressive
    -0.07
     consp
    -0.07
     avis
    -0.07
    val
    -0.07
    consume
    -0.07
    POSITIVE LOGITS
    /sec
    0.09
     fréquent
    0.08
     sopra
    0.08
     encima
    0.08
     �
    0.08
     Alto
    0.07
    ){
    0.07
    elift
    0.07
    }.{
    0.07
    /th
    0.07
    Activations Density 0.002%

    No Known Activations