© 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. 11-RESID-POST-AA
    11. 110885
    Prev
    Next
    INDEX
    Explanations

    Absolute value math equations

    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
     UIBar
    -0.09
     bpy
    -0.08
     descubr
    -0.08
    '];?>"
    -0.08
     establecer
    -0.08
     Fortsch
    -0.08
     encontro
    -0.08
     discovered
    -0.08
    窥
    -0.08
    发现
    -0.07
    POSITIVE LOGITS
    >-
    0.08
    റിയ
    0.08
    Generally
    0.07
     regimes
    0.07
    ോണ
    0.07
    )is
    0.07
    ondon
    0.07
    xml
    0.07
     xml
    0.07
    _conditions
    0.07
    Activations Density 0.030%

    No Known Activations