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. 23252
    Prev
    Next
    INDEX
    Explanations

    Racing against time

    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
    យ
    -0.09
    /mac
    -0.08
     apareceu
    -0.08
    ਕੀ
    -0.08
     stayed
    -0.08
     hydrated
    -0.08
    বো
    -0.08
     textbook
    -0.08
     textbooks
    -0.08
     plante
    -0.07
    POSITIVE LOGITS
     ascending
    0.08
    ascending
    0.08
     процедура
    0.07
     भय
    0.07
     подачи
    0.07
     Verfahren
    0.07
    (true
    0.07
     government's
    0.07
    _CLOCK
    0.07
     strangers
    0.07
    Activations Density 0.009%

    No Known Activations