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. 129901
    Prev
    Next
    INDEX
    Explanations

    addressing people formally

    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
    _sync
    -0.09
    _SYNC
    -0.09
    天然
    -0.08
    玩法
    -0.08
     Subsid
    -0.08
     ergo
    -0.08
    .Sync
    -0.08
     consequência
    -0.08
    同步
    -0.07
    	enable
    -0.07
    POSITIVE LOGITS
     respectfully
    0.10
     höf
    0.10
     respectful
    0.09
     recipients
    0.09
     etiquette
    0.09
     politely
    0.09
     hó
    0.09
     courteous
    0.08
     фам
    0.08
     Sheridan
    0.08
    Activations Density 0.011%

    No Known Activations