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. 42150
    Prev
    Next
    INDEX
    Explanations

    Thinking and re-evaluating

    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
     preferably
    -0.08
     сап
    -0.08
     burdens
    -0.07
     갖
    -0.07
    'ont
    -0.07
     ???↵↵
    -0.07
     এমন
    -0.07
    'am
    -0.07
    'ın
    -0.07
     #-}↵↵
    -0.07
    POSITIVE LOGITS
    joins
    0.08
     rundt
    0.08
    而言
    0.08
     glance
    0.08
    gevo
    0.08
    起来
    0.08
    来说
    0.07
    حص
    0.07
    看来
    0.07
    leo
    0.07
    Activations Density 0.010%

    No Known Activations