© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54855
    Prev
    Next
    INDEX
    Explanations

    Romance languages

    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
    ಿದ್ಯ
    -0.08
    ：「
    -0.08
    ுத
    -0.08
    ೋ
    -0.08
     шумо
    -0.08
     Zuma
    -0.08
     puls
    -0.08
    ಿಯೋ
    -0.08
    ுதி
    -0.08
     سید
    -0.08
    POSITIVE LOGITS
     �
    0.10
     version
    0.09
    version
    0.09
    �
    0.09
     nationality
    0.08
     langue
    0.08
     traduz
    0.08
     tradu
    0.08
     locale
    0.08
    _VERSION
    0.08
    Activations Density 0.092%

    No Known Activations