© 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. 11-RESID-POST-AA
    11. 26129
    Prev
    Next
    INDEX
    Explanations

    primes

    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
     värld
    -0.08
     миров
    -0.08
     ->↵
    -0.08
     ^{↵
    -0.08
    лиг
    -0.07
    egd
    -0.07
    اديم
    -0.07
    සර
    -0.07
     ambassade
    -0.07
    Depending
    -0.07
    POSITIVE LOGITS
     işe
    0.07
     iter
    0.07
     edil
    0.07
     São
    0.07
     FORM
    0.07
    ऽ
    0.07
     scour
    0.07
     garlic
    0.07
     pagh
    0.07
    0.07
    Activations Density 0.003%
    No Known Activations