© 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. 112329
    Prev
    Next
    INDEX
    Explanations

    Planes and intersections

    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
     dividends
    -0.09
     cyfr
    -0.08
    .'.
    -0.08
    .calls
    -0.08
     outsourced
    -0.08
    ARGV
    -0.08
     رضي
    -0.08
    >>,
    -0.08
     molinos
    -0.08
     withdrawals
    -0.08
    POSITIVE LOGITS
     wedge
    0.08
     Kinect
    0.08
    0.08
    组三
    0.08
    imu
    0.08
     trid
    0.08
    pendicular
    0.08
     terceira
    0.08
    planes
    0.08
    -horizontal
    0.07
    Activations Density 0.019%
    No Known Activations