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

    Neuronpedia

    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. 7-RESID-POST-AA
    11. 834
    Prev
    Next
    INDEX
    Explanations

    conjunctions introducing clauses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edent
    -0.07
     blo
    -0.07
     Bla
    -0.07
     Bloc
    -0.07
     Achat
    -0.07
     voren
    -0.07
    -c
    -0.07
     pleno
    -0.07
     métall
    -0.07
     impecc
    -0.07
    POSITIVE LOGITS
    989
    0.08
    539
    0.07
    一下
    0.07
    rous
    0.07
     impressed
    0.07
     потер
    0.07
    738
    0.07
     mà
    0.07
     टोली
    0.07
    व्ह
    0.07
    Activations Density 0.010%

    No Known Activations