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. 87986
    Prev
    Next
    INDEX
    Explanations

    EOQ formula

    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
     science
    -0.09
    亚洲区
    -0.08
     Baden
    -0.08
    Science
    -0.08
    =head
    -0.08
     Budapest
    -0.08
     noodles
    -0.08
     Science
    -0.07
     bpm
    -0.07
     collège
    -0.07
    POSITIVE LOGITS
     annual
    0.10
    annual
    0.10
     annually
    0.10
    Annual
    0.10
     Annual
    0.10
     ખર્ચ
    0.09
    elastic
    0.09
     sunk
    0.09
     Retail
    0.09
     incurred
    0.09
    Activations Density 0.003%

    No Known Activations