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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 113566
    Prev
    Next
    INDEX
    Explanations

    coalition

    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
     Processor
    -0.09
     unaffected
    -0.09
     lateral
    -0.08
    ulk
    -0.08
    _Pl
    -0.07
     Shortcut
    -0.07
     lok
    -0.07
     Resp
    -0.07
     Parallel
    -0.07
     Batch
    -0.07
    POSITIVE LOGITS
     coalition
    0.12
     alliances
    0.10
    伙伴
    0.09
    合わせ
    0.09
     consortium
    0.08
    Variants
    0.08
    联盟
    0.08
    广西
    0.08
    合作
    0.08
    
    0.08
    Activations Density 0.007%

    No Known Activations