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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9265
    Prev
    Next
    INDEX
    Explanations

    work/job

    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
    CEP
    -0.08
     kosong
    -0.08
     мг
    -0.08
     chiến
    -0.08
    mpl
    -0.08
    _alive
    -0.08
     cheminée
    -0.08
     strumenti
    -0.08
    .groupby
    -0.07
     mom
    -0.07
    POSITIVE LOGITS
     workmanship
    0.10
     craftsmanship
    0.09
     expertly
    0.08
     cosmet
    0.08
     맡
    0.07
     renovation
    0.07
     sanding
    0.07
     بطريقة
    0.07
     repairs
    0.07
     wir
    0.07
    Activations Density 0.051%

    No Known Activations