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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RESID-POST-AA
    11. 112557
    Prev
    Next
    INDEX
    Explanations

    graphene

    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
     sitcom
    -0.09
     textbox
    -0.09
     magazine
    -0.09
     '&
    -0.08
    campaign
    -0.08
     cemetery
    -0.08
     wagering
    -0.07
     Reagan
    -0.07
     "&
    -0.07
    _lt
    -0.07
    POSITIVE LOGITS
     graphene
    0.16
     exfol
    0.12
     pristine
    0.11
     ethereum
    0.11
     carbon
    0.10
     silic
    0.10
    Ethereum
    0.10
     nanos
    0.09
     Ethereum
    0.09
     nano
    0.09
    Activations Density 0.008%

    No Known Activations