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. 58916
    Prev
    Next
    INDEX
    Explanations

    Guan Yin

    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
    INTRO
    -0.07
    -after
    -0.07
     associates
    -0.07
    (URL
    -0.07
    determ
    -0.07
    thr
    -0.07
     రోజుల
    -0.07
     Part
    -0.06
     liabilities
    -0.06
     हिस्स
    -0.06
    POSITIVE LOGITS
    �
    0.09
     تعالى
    0.09
     сант
    0.09
     如意
    0.09
     weighing
    0.09
     ﷺ
    0.08
     多宝
    0.08
     تعالیٰ
    0.08
    ****
    0.08
     �
    0.08
    Activations Density 0.003%

    No Known Activations