© 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. 51145
    Prev
    Next
    INDEX
    Explanations

    gl

    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
     chemical
    -0.08
    锡
    -0.08
     cast
    -0.08
     valt
    -0.08
     olin
    -0.08
     isto
    -0.07
     целом
    -0.07
    chemical
    -0.07
     化
    -0.07
    ходим
    -0.07
    POSITIVE LOGITS
    set
    0.11
    (set
    0.09
    sets
    0.08
    ក
    0.08
    setzen
    0.08
    setzt
    0.08
    Author
    0.07
    Exception
    0.07
    ways
    0.07
    င့်
    0.07
    Activations Density 0.000%

    No Known Activations