© 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. 11-RESID-POST-AA
    11. 31191
    Prev
    Next
    INDEX
    Explanations

    Outdoor attached spaces

    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
     collisions
    -0.08
     കണ്ണ
    -0.08
     Polize
    -0.08
     collision
    -0.08
     collide
    -0.07
    _collision
    -0.07
    vey
    -0.07
    estown
    -0.07
    collision
    -0.07
     આંખ
    -0.07
    POSITIVE LOGITS
     patio
    0.12
     patios
    0.11
     varanda
    0.10
     terraza
    0.09
     balcony
    0.09
     terrace
    0.09
     veranda
    0.09
     Patio
    0.09
     verand
    0.08
     balconies
    0.08
    Activations Density 0.026%

    No Known Activations