© 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. 23-RESID-POST-AA
    11. 48645
    Prev
    Next
    INDEX
    Explanations

    bootstrap

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Boeing
    -0.09
     Warwick
    -0.08
     삼성
    -0.08
     �
    -0.08
     SARS
    -0.08
    .lwjgl
    -0.08
    opi
    -0.07
    remain
    -0.07
    banks
    -0.07
     wart
    -0.07
    POSITIVE LOGITS
     Icons
    0.13
     CDN
    0.13
    	Grid
    0.13
     Grid
    0.13
     grid
    0.12
    	grid
    0.12
     Carousel
    0.11
     Tooltip
    0.11
     Modal
    0.11
     Date
    0.11
    Activations Density 0.003%

    No Known Activations