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. 43103
    Prev
    Next
    INDEX
    Explanations

    Broad, everyday topics

    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
     comprend
    -0.08
     fanc
    -0.08
     either
    -0.08
     luwih
    -0.07
     entweder
    -0.07
    环
    -0.07
     jai
    -0.07
     più
    -0.07
     más
    -0.07
    /local
    -0.07
    POSITIVE LOGITS
    なので
    0.09
     હોવાથી
    0.09
    所以
    0.09
    _FINAL
    0.08
     وعدم
    0.08
     acost
    0.08
     môže
    0.08
     betreft
    0.08
     understandably
    0.08
    背景
    0.08
    Activations Density 0.148%

    No Known Activations