© 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. 23-RESID-POST-AA
    11. 49757
    Prev
    Next
    INDEX
    Explanations

    Middle Eastern foods

    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
     Missouri
    -0.11
     Alaska
    -0.10
     Manitoba
    -0.09
     Kansas
    -0.09
     Wisconsin
    -0.09
     Iowa
    -0.09
     squirrel
    -0.09
     Macau
    -0.09
    maine
    -0.09
    树林
    -0.09
    POSITIVE LOGITS
     babagan
    0.19
     pita
    0.17
     feta
    0.17
     za
    0.16
     tah
    0.16
     тах
    0.15
     zaal
    0.15
     Lebanese
    0.15
     Middle
    0.15
     তাহ
    0.15
    Activations Density 0.028%

    No Known Activations