© 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. 31012
    Prev
    Next
    INDEX
    Explanations

    ar

    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
     achievable
    -0.09
     achat
    -0.08
     网上
    -0.08
     ordine
    -0.08
    ackage
    -0.07
     attainable
    -0.07
    ••
    -0.07
     사실
    -0.07
    eso
    -0.07
     preco
    -0.07
    POSITIVE LOGITS
     рус
    0.10
     запад
    0.08
    @
    0.08
    シ
    0.08
    @\
    0.07
    /@
    0.07
     gericht
    0.07
     한국
    0.07
     Western
    0.07
     россий
    0.07
    Activations Density 0.002%

    No Known Activations