© 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. 11-RESID-POST-AA
    11. 99450
    Prev
    Next
    INDEX
    Explanations

    residences

    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
     معرفة
    -0.09
     Hora
    -0.08
     rates
    -0.08
     муҳим
    -0.08
     Earth's
    -0.08
     förstå
    -0.08
     extrap
    -0.07
    (Module
    -0.07
     enabling
    -0.07
     forstå
    -0.07
    POSITIVE LOGITS
    入住
    0.15
     occupants
    0.14
     occupying
    0.11
    Occup
    0.11
     occupant
    0.11
     occupancy
    0.10
     bewoners
    0.10
     wohnen
    0.10
     verhuis
    0.10
     ocupar
    0.10
    Activations Density 0.064%

    No Known Activations