© 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. 112332
    Prev
    Next
    INDEX
    Explanations

    compensation

    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
     gecon
    -0.07
    ，很
    -0.07
    hema
    -0.07
    募
    -0.07
    马克
    -0.07
     사이
    -0.07
     hasard
    -0.07
     ಸಾಲ
    -0.07
     abruptly
    -0.07
     Russo
    -0.07
    POSITIVE LOGITS
     compensation
    0.12
     compensate
    0.11
     compens
    0.11
     компенса
    0.11
     компен
    0.10
     Compensation
    0.10
     correction
    0.10
     accounting
    0.10
     устран
    0.10
     correcting
    0.10
    Activations Density 0.007%

    No Known Activations