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. 90050
    Prev
    Next
    INDEX
    Explanations

    phrase

    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
     gespannt
    -0.08
     surv
    -0.07
     cate
    -0.07
     CPM
    -0.07
     pourra
    -0.07
     senior
    -0.07
     pourrez
    -0.07
     вы
    -0.07
     canopy
    -0.07
    Su
    -0.07
    POSITIVE LOGITS
     adicional
    0.09
    처럼
    0.09
     뒤
    0.08
     λόγω
    0.08
     này
    0.08
     tersebut
    0.08
    后的
    0.08
    _BYTES
    0.08
     السابقة
    0.08
    หลัง
    0.08
    Activations Density 0.013%

    No Known Activations