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. 60547
    Prev
    Next
    INDEX
    Explanations

    superconductivity

    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
     apron
    -0.09
     accountability
    -0.09
     EVP
    -0.08
     Accountability
    -0.08
     Adobe
    -0.08
     evangel
    -0.08
    Fleet
    -0.08
     distributing
    -0.08
     scripture
    -0.08
     apost
    -0.08
    POSITIVE LOGITS
     phenomena
    0.16
     superconduct
    0.14
     quantum
    0.13
     phenomenon
    0.13
    Quantum
    0.12
     Quantum
    0.12
     physics
    0.11
     doping
    0.10
    Physics
    0.10
     Physics
    0.10
    Activations Density 0.007%

    No Known Activations