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. 76143
    Prev
    Next
    INDEX
    Explanations

    remove

    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
     mittels
    -0.08
     olha
    -0.08
     ==↵
    -0.07
    arrival
    -0.07
     einem
    -0.07
    ಗೆ
    -0.07
     aiki
    -0.07
    لل
    -0.07
     ಕಾರ್ಯ
    -0.07
     alcanzar
    -0.07
    POSITIVE LOGITS
    Removed
    0.11
     unnecessary
    0.11
     лиш
    0.11
    (remove
    0.10
    Remove
    0.10
     altogether
    0.10
    /remove
    0.10
    .Remove
    0.10
    不要
    0.10
     removing
    0.10
    Activations Density 0.020%

    No Known Activations