© 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. 95374
    Prev
    Next
    INDEX
    Explanations

    no

    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
    Scatter
    -0.09
     Scatter
    -0.08
     scatter
    -0.07
    �
    -0.07
     moot
    -0.07
     artific
    -0.07
     hash
    -0.07
     alkal
    -0.07
    706
    -0.07
     termed
    -0.06
    POSITIVE LOGITS
     ผ่าน
    0.09
     chuyện
    0.09
    ใต้
    0.09
    เพลง
    0.08
    -в
    0.08
    เสียง
    0.08
    誘惑
    0.08
     Anders
    0.08
     თქ
    0.08
     accompagner
    0.08
    Activations Density 0.011%

    No Known Activations