© 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. 78942
    Prev
    Next
    INDEX
    Explanations

    [-

    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
     Italy
    -0.08
    go
    -0.07
    atur
    -0.07
    melding
    -0.07
    gemaakt
    -0.07
     independent
    -0.07
    provements
    -0.07
     accompanying
    -0.07
     Capri
    -0.07
    vars
    -0.07
    POSITIVE LOGITS
     Palais
    0.10
     jednost
    0.09
     xona
    0.08
    ihak
    0.08
     древес
    0.08
    έρα
    0.08
     શોધ
    0.08
     парков
    0.08
     palais
    0.08
    런
    0.08
    Activations Density 0.045%

    No Known Activations