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. 61025
    Prev
    Next
    INDEX
    Explanations

    set

    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
     curvature
    -0.07
    “大
    -0.07
    Пом
    -0.07
    Quadr
    -0.07
     revol
    -0.07
    Ţ
    -0.07
    法院
    -0.07
    ೀ
    -0.07
    的大
    -0.07
    划
    -0.07
    POSITIVE LOGITS
     afterwards
    0.12
     anschließend
    0.12
     Afterwards
    0.11
     afterward
    0.11
     वापस
    0.11
     પાછ
    0.11
     kembali
    0.10
     വീണ്ടും
    0.10
     selesai
    0.10
     ফিরে
    0.10
    Activations Density 0.015%

    No Known Activations