© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51414
    Prev
    Next
    INDEX
    Explanations

    warehouse

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saludo
    -0.09
     jailbreak
    -0.09
    UIText
    -0.09
     csrf
    -0.08
     hairst
    -0.08
     spokesperson
    -0.08
     scissors
    -0.08
     spoof
    -0.08
     autofocus
    -0.08
     proqram
    -0.08
    POSITIVE LOGITS
     warehouse
    0.25
     warehouses
    0.22
     Warehouse
    0.21
    warehouse
    0.21
    Warehouse
    0.21
     lake
    0.20
    仓
    0.19
     marts
    0.18
     ware
    0.17
     Ware
    0.17
    Activations Density 0.016%

    No Known Activations