© 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. 114343
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     Fibonacci
    -0.09
    .maven
    -0.09
     imperial
    -0.09
    Egypt
    -0.08
     Volley
    -0.08
     Cite
    -0.08
     Coastal
    -0.08
     egypt
    -0.08
     docking
    -0.08
     tank
    -0.08
    POSITIVE LOGITS
     measurable
    0.09
     demean
    0.09
     rémun
    0.09
    conv
    0.09
     suprem
    0.08
     conm
    0.08
     convicted
    0.08
    orte
    0.08
     оператор
    0.08
    ulog
    0.08
    Activations Density 0.011%

    No Known Activations