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. 119197
    Prev
    Next
    INDEX
    Explanations

    colon

    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
     restauration
    -0.08
    恢
    -0.08
    احت
    -0.08
    وان
    -0.07
    یر
    -0.07
     aforementioned
    -0.07
     Ser
    -0.07
     perspekt
    -0.07
    _ser
    -0.07
    رسال
    -0.07
    POSITIVE LOGITS
     fgets
    0.08
     newline
    0.07
     Ami
    0.07
     나는
    0.07
     қой
    0.07
     fa
    0.07
     reopening
    0.07
    ところ
    0.07
     fis
    0.07
     fscanf
    0.07
    Activations Density 0.006%

    No Known Activations