© 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. 99265
    Prev
    Next
    INDEX
    Explanations

    all/every

    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
     दिनों
    -0.08
     días
    -0.08
    Bride
    -0.08
    یاں
    -0.08
     days
    -0.07
     troubleshoot
    -0.07
     straightforward
    -0.07
     agradable
    -0.07
     वर्षों
    -0.07
    Aquí
    -0.07
    POSITIVE LOGITS
    _except
    0.11
     أنحاء
    0.11
     تقريب
    0.10
     nationwide
    0.09
     minden
    0.09
    ทุก
    0.09
     conceivable
    0.09
     everyone
    0.09
     Eligible
    0.08
     except
    0.08
    Activations Density 0.063%

    No Known Activations