© 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. 68890
    Prev
    Next
    INDEX
    Explanations

    office

    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
     theoret
    -0.08
    سة
    -0.08
    ielo
    -0.08
    ihi
    -0.08
    ereo
    -0.08
    Website
    -0.07
    INESS
    -0.07
     doesn't
    -0.07
    ibig
    -0.07
    Filesystem
    -0.07
    POSITIVE LOGITS
     леп
    0.08
     lubrication
    0.08
     хан
    0.08
    orte
    0.08
     concili
    0.07
     استعداد
    0.07
    Destino
    0.07
     осв
    0.07
     lubric
    0.07
     ligging
    0.07
    Activations Density 0.017%

    No Known Activations