© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102148
    Prev
    Next
    INDEX
    Explanations

    char

    np_max-act-logits · gemini-2.0-flash
    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
    adeed
    -0.08
    grö
    -0.07
    ght
    -0.07
    hpp
    -0.07
    .Take
    -0.07
     çünkü
    -0.07
     roofs
    -0.07
    .Lerp
    -0.07
     collecting
    -0.07
    elm
    -0.07
    POSITIVE LOGITS
     არის
    0.09
    езульт
    0.09
     נראה
    0.09
    	service
    0.09
     имеется
    0.09
    ың
    0.08
     буквально
    0.08
    当に
    0.08
    Concurrency
    0.08
     დაახლოებით
    0.08
    Activations Density 0.000%

    No Known Activations