© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 47533
    Prev
    Next
    INDEX
    Explanations

    urban planning and architecture

    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
    -0.09
     Yon
    -0.09
     Appalach
    -0.08
     Formation
    -0.08
     Peak
    -0.08
     Так
    -0.07
     Shelley
    -0.07
     Soil
    -0.07
     Creativity
    -0.07
     Stove
    -0.07
    POSITIVE LOGITS
     planned
    0.12
     defensive
    0.12
     civic
    0.12
     monumental
    0.12
     ceremonial
    0.11
     judicial
    0.11
     fortified
    0.11
     episc
    0.10
     bishop
    0.10
     palace
    0.10
    Activations Density 0.022%

    No Known Activations