© 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. 7-RESID-POST-AA
    11. 1248
    Prev
    Next
    INDEX
    Explanations

    Supersonic air travel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     daran
    -0.08
    थम
    -0.07
     mówi
    -0.07
    ,the
    -0.07
     soci
    -0.07
     durata
    -0.07
    zi
    -0.07
    �
    -0.07
    300
    -0.07
    Geom
    -0.07
    POSITIVE LOGITS
    פס
    0.08
     основе
    0.08
     отра
    0.08
    ுக்
    0.08
     ATA
    0.07
    anye
    0.07
    elte
    0.07
     taxing
    0.07
    -lib
    0.07
    عر
    0.07
    Activations Density 0.000%

    No Known Activations