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. 67241
    Prev
    Next
    INDEX
    Explanations

    mixed languages/translation

    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
     сним
    -0.08
    comod
    -0.08
    Placed
    -0.07
    _dyn
    -0.07
    moil
    -0.07
    IDL
    -0.07
     stel
    -0.07
     novel
    -0.07
     устанавли
    -0.07
     coop
    -0.07
    POSITIVE LOGITS
    님
    0.11
    님의
    0.11
    께
    0.09
     العزيز
    0.09
    帅
    0.09
    傅
    0.09
     :)↵↵
    0.08
     সামনে
    0.08
     ấy
    0.08
    先生
    0.08
    Activations Density 0.022%

    No Known Activations