Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12611
    Prev
    Next
    INDEX
    Explanations

    math calculations

    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
    ekom
    -0.08
     Hd
    -0.08
    #set
    -0.08
    喜欢
    -0.08
     നേടിയ
    -0.07
    hg
    -0.07
     идеи
    -0.07
     Pond
    -0.07
    溪县
    -0.07
     Domin
    -0.07
    POSITIVE LOGITS
    —all
    0.10
    等等
    0.08
     Lastly
    0.08
     lainnya
    0.07
     その他
    0.07
     schließlich
    0.07
     Finally
    0.07
    urals
    0.07
    チェ
    0.07
     기타
    0.07
    Activations Density 0.119%

    No Known Activations