© 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. 31035
    Prev
    Next
    INDEX
    Explanations

    falling through air

    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
     coloc
    -0.08
     Planning
    -0.08
     lua
    -0.07
     procéd
    -0.07
     adding
    -0.07
    argout
    -0.07
     colleague
    -0.07
    kum
    -0.07
     checking
    -0.07
     exact
    -0.07
    POSITIVE LOGITS
     aerodynamic
    0.13
     аэр
    0.11
     airborne
    0.10
     aer
    0.10
    _drag
    0.09
    Drag
    0.09
    空气
    0.09
     الهواء
    0.09
     стаб
    0.09
     рак
    0.09
    Activations Density 0.013%

    No Known Activations