© 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. 63246
    Prev
    Next
    INDEX
    Explanations

    Sports analysis

    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
     muodost
    -0.08
    poch
    -0.08
     AWS
    -0.07
     achieve
    -0.07
     torno
    -0.07
     ind
    -0.07
     whisk
    -0.07
     सिर्�
    -0.07
    .camel
    -0.07
     syscall
    -0.07
    POSITIVE LOGITS
     forensic
    0.09
    Karl
    0.09
    <Game
    0.08
     intelligence
    0.08
     burglary
    0.08
     Tires
    0.08
     nuit
    0.08
     computers
    0.08
     Intelligence
    0.08
    Computer
    0.08
    Activations Density 0.024%

    No Known Activations