© 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. 11-RESID-POST-AA
    11. 29776
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    爱的
    -0.07
    面的
    -0.07
     protest
    -0.07
     Newport
    -0.07
     dini
    -0.07
     Dit
    -0.07
     Coff
    -0.06
     Designed
    -0.06
     Court
    -0.06
    .Errorf
    -0.06
    POSITIVE LOGITS
     Europees
    0.08
     publik
    0.08
    asyonal
    0.08
     oldal
    0.08
     mūsu
    0.08
     differential
    0.08
     נוסף
    0.08
    akalo
    0.08
    ések
    0.07
    씩
    0.07
    Activations Density 0.194%

    No Known Activations