© 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. 23-RESID-POST-AA
    11. 96479
    Prev
    Next
    INDEX
    Explanations

    institutions or organizations

    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
    able
    -0.09
     stolen
    -0.08
     provenant
    -0.08
     thief
    -0.07
     discarded
    -0.07
     tilgjeng
    -0.07
     extrema
    -0.07
     provenientes
    -0.07
     Filename
    -0.07
     ಮೋ
    -0.07
    POSITIVE LOGITS
     headquartered
    0.22
    总部
    0.20
     headquarters
    0.19
     সদর
    0.18
     sponsoring
    0.17
    运营
    0.17
    法人
    0.17
     gevestigd
    0.17
     Headquarters
    0.16
     opgericht
    0.16
    Activations Density 0.134%

    No Known Activations