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. 59510
    Prev
    Next
    INDEX
    Explanations

    sports injuries

    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
     commodity
    -0.08
     Hello
    -0.07
     赤
    -0.07
     locator
    -0.07
     Popular
    -0.07
     Sur
    -0.07
     Blackboard
    -0.07
    _sur
    -0.07
     sur
    -0.07
     racc
    -0.07
    POSITIVE LOGITS
     künftig
    0.10
     Ono
    0.08
     reportedly
    0.08
     diagnosed
    0.08
    DY
    0.08
    ength
    0.08
     offseason
    0.08
    �്
    0.08
    ��
    0.08
    among
    0.08
    Activations Density 0.010%

    No Known Activations