© 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. 48031
    Prev
    Next
    INDEX
    Explanations

    foreign suffixes

    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
     efectivo
    -0.10
    ENT
    -0.08
    HOT
    -0.08
     Dist
    -0.08
     ent
    -0.08
    ಿಣ
    -0.08
    endforeach
    -0.08
    шино
    -0.08
    шо
    -0.08
    ಿನ್ನ
    -0.08
    POSITIVE LOGITS
    אַנס
    0.26
    ൻസ്
    0.26
    ન્સ
    0.26
    েন্স
    0.25
    ance
    0.25
    ेंस
    0.24
    անս
    0.23
    ANCE
    0.23
    न्स
    0.23
    ાન્સ
    0.22
    Activations Density 0.035%

    No Known Activations