© 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. 23-RESID-POST-AA
    11. 96661
    Prev
    Next
    INDEX
    Explanations

    logical

    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
     circa
    -0.09
     auster
    -0.09
    ريات
    -0.09
     approximation
    -0.09
     apparaten
    -0.09
     botas
    -0.08
     Approx
    -0.08
     دستگاه
    -0.08
     تقریب
    -0.08
     animales
    -0.08
    POSITIVE LOGITS
     logical
    0.15
     tenant
    0.15
    logical
    0.14
    Logical
    0.14
    逻
    0.14
     logically
    0.13
    Tenant
    0.13
    tenant
    0.13
     Logical
    0.12
     tenancy
    0.12
    Activations Density 0.007%

    No Known Activations