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. 77216
    Prev
    Next
    INDEX
    Explanations

    Science

    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
     जब
    -0.08
     digs
    -0.08
     тура
    -0.08
     correlate
    -0.08
     creative
    -0.07
     Loch
    -0.07
     Pamp
    -0.07
    chod
    -0.07
     když
    -0.07
    焼
    -0.07
    POSITIVE LOGITS
    news
    0.09
     junk
    0.09
    News
    0.08
    sd
    0.08
    junk
    0.08
     konusunda
    0.08
    -The
    0.07
    》(
    0.07
     Handbook
    0.07
    》
    0.07
    Activations Density 0.056%

    No Known Activations