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

    Neuronpedia

    Jacobian LensNEW
    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. 112615
    Prev
    Next
    INDEX
    Explanations

    chairs

    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
     দ্ব
    -0.08
     contaminación
    -0.08
     reactors
    -0.08
     pokemon
    -0.08
     pojed
    -0.08
     público
    -0.08
     bids
    -0.07
     domest
    -0.07
     biv
    -0.07
     bid
    -0.07
    POSITIVE LOGITS
     upholstered
    0.10
    supports
    0.09
    Supports
    0.09
     shaded
    0.09
    Automatic
    0.09
    -LAST
    0.08
    automatic
    0.08
     вентиля
    0.08
    脸
    0.08
     reclining
    0.08
    Activations Density 0.012%

    No Known Activations