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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 47033
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     લઈ
    -0.09
    ,而且
    -0.09
     autant
    -0.08
     😉
    -0.08
     পূ
    -0.08
     wirklich
    -0.07
     ખર
    -0.07
     whatever
    -0.07
     Мне
    -0.07
    χεί
    -0.07
    POSITIVE LOGITS
    数据显示
    0.09
     hingegen
    0.08
     naman
    0.08
     schließlich
    0.08
     spé
    0.07
     onwards
    0.07
     ANI
    0.07
    uld
    0.07
     Develop
    0.07
    에서는
    0.07
    Activations Density 0.057%

    No Known Activations