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. 53472
    Prev
    Next
    INDEX
    Explanations

    Taking something seriously

    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
    पर
    -0.09
    Passing
    -0.09
    _BT
    -0.07
     Blake
    -0.07
     passando
    -0.07
     排
    -0.07
    ंटर
    -0.07
     हाथ
    -0.07
     dérou
    -0.07
    经过
    -0.07
    POSITIVE LOGITS
     משמעות
    0.10
     سمجھ
    0.10
     consequential
    0.10
     serius
    0.09
     enthusiasm
    0.09
     seriously
    0.09
     nghi
    0.09
     меры
    0.09
     গুরুত্ব
    0.09
     સમજ
    0.09
    Activations Density 0.027%

    No Known Activations