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. 113864
    Prev
    Next
    INDEX
    Explanations

    from

    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
     вруч
    -0.08
     presencial
    -0.08
     введ
    -0.07
     purposely
    -0.07
     regras
    -0.07
     Voilà
    -0.07
    licenses
    -0.07
     deliberately
    -0.07
     intentionally
    -0.07
    工商
    -0.07
    POSITIVE LOGITS
     слишком
    0.11
     túl
    0.10
     mildew
    0.09
     troppo
    0.09
     demasi
    0.09
     ज्यादा
    0.09
     overe
    0.09
     demasiado
    0.09
     bị
    0.08
     overheating
    0.08
    Activations Density 0.018%

    No Known Activations