© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51247
    Prev
    Next
    INDEX
    Explanations

    O-rings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     চিক
    -0.08
     Tilt
    -0.08
     Merge
    -0.08
    Tilt
    -0.08
    .horizontal
    -0.08
    柜
    -0.08
    _SAFE
    -0.07
    unten
    -0.07
    Merge
    -0.07
    逸
    -0.07
    POSITIVE LOGITS
     O
    0.12
     rings
    0.11
    O
    0.10
     o
    0.10
     коль
    0.09
     ring
    0.09
     bushes
    0.09
     petals
    0.09
     шай
    0.09
     gland
    0.09
    Activations Density 0.013%

    No Known Activations