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. 129764
    Prev
    Next
    INDEX
    Explanations

    vh

    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
     Wide
    -0.08
     transferência
    -0.08
     الن
    -0.08
    ons
    -0.08
     국제
    -0.08
     আন্তর্জাতিক
    -0.07
     szere
    -0.07
     Zip
    -0.07
    _n
    -0.07
     SIM
    -0.07
    POSITIVE LOGITS
    -height
    0.10
     allocated
    0.09
     height
    0.09
     allocate
    0.09
    /footer
    0.09
    -bottom
    0.09
    bottom
    0.09
     stature
    0.09
     allotted
    0.08
    height
    0.08
    Activations Density 0.011%

    No Known Activations