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. 49033
    Prev
    Next
    INDEX
    Explanations

    regex and discussions

    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
    ducation
    -0.09
    urve
    -0.08
    로
    -0.08
    hood
    -0.08
    ffee
    -0.07
    duc
    -0.07
    grade
    -0.07
    atur
    -0.07
     સમજ
    -0.07
    ்ந்து
    -0.07
    POSITIVE LOGITS
     stagger
    0.09
    ివ్
    0.08
    tono
    0.08
     חת
    0.08
     ورت
    0.08
     صباح
    0.07
    0.07
     :-)↵
    0.07
     איר
    0.07
    ైత
    0.07
    Activations Density 0.000%

    No Known Activations