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. 44217
    Prev
    Next
    INDEX
    Explanations

    crank

    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
    .Te
    -0.07
     FROM
    -0.07
     treatment
    -0.07
     locations
    -0.07
    PY
    -0.07
     sites
    -0.07
    দ
    -0.07
    isha
    -0.07
    (++
    -0.07
    ****************
    -0.07
    POSITIVE LOGITS
    歷
    0.09
    .refresh
    0.09
    	refresh
    0.09
     इतिहास
    0.09
     आवश्यकता
    0.08
    _manual
    0.08
    飞艇
    0.08
    刷新
    0.08
     آسیاب
    0.08
     होकर
    0.08
    Activations Density 0.005%

    No Known Activations