© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103384
    Prev
    Next
    INDEX
    Explanations

    OPC

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fleas
    -0.09
     Airbnb
    -0.09
    urricane
    -0.09
    ২২
    -0.08
    微博
    -0.08
    invoice
    -0.08
     habitats
    -0.08
     planeta
    -0.08
     installment
    -0.08
     installments
    -0.08
    POSITIVE LOGITS
     OPC
    0.16
     historian
    0.14
     Histor
    0.13
     historians
    0.12
     PLC
    0.12
     DA
    0.11
     histor
    0.11
     UA
    0.10
     H
    0.10
    PLC
    0.10
    Activations Density 0.011%

    No Known Activations