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. 104080
    Prev
    Next
    INDEX
    Explanations

    code

    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
     ducts
    -0.08
    quitos
    -0.08
    ":[{↵
    -0.08
     Loz
    -0.08
    ющими
    -0.07
     യ
    -0.07
    日上午
    -0.07
     muren
    -0.07
     Mc
    -0.07
    다는
    -0.07
    POSITIVE LOGITS
     ciência
    0.07
    iveness
    0.07
    	list
    0.07
    ainer
    0.07
    front
    0.07
     eletr
    0.07
    	raw
    0.07
     puer
    0.07
     usefulness
    0.07
    Medicine
    0.07
    Activations Density 0.001%

    No Known Activations