© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 95373
    Prev
    Next
    INDEX
    Explanations

    smart home protocols

    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
     doubling
    -0.09
     doubled
    -0.08
    dup
    -0.08
     blat
    -0.08
    (Config
    -0.08
    oint
    -0.08
     Taj
    -0.08
     folds
    -0.07
     gigant
    -0.07
    .rank
    -0.07
    POSITIVE LOGITS
     Umb
    0.09
     oz
    0.08
     Zig
    0.08
    Umb
    0.08
     companionship
    0.08
     hué
    0.08
     Consortium
    0.08
     comerc
    0.07
    Hibernate
    0.07
    ishini
    0.07
    Activations Density 0.002%

    No Known Activations