Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 60655
    Prev
    Next
    INDEX
    Explanations

    air quality

    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
     floppy
    -0.10
     crossword
    -0.08
    hemm
    -0.08
     sej
    -0.08
     tape
    -0.08
     Insolvenz
    -0.07
     screws
    -0.07
     entrevista
    -0.07
     This
    -0.07
     diagram
    -0.07
    POSITIVE LOGITS
     pollutants
    0.16
     pollut
    0.15
     pollution
    0.13
     Pollution
    0.12
    污染
    0.12
     inhal
    0.11
     EPA
    0.11
     polluted
    0.10
     contaminación
    0.10
     શહેર
    0.10
    Activations Density 0.018%

    No Known Activations