© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 91605
    Prev
    Next
    INDEX
    Explanations

    marginal utility, economics

    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
    Scratch
    -0.08
     Amit
    -0.08
     Cord
    -0.08
     cord
    -0.08
     Scratch
    -0.08
     Ami
    -0.08
     Lightning
    -0.08
     volet
    -0.07
    Pam
    -0.07
    Salon
    -0.07
    POSITIVE LOGITS
     incremental
    0.16
     increments
    0.14
    increment
    0.14
     increment
    0.13
    increments
    0.12
    Increment
    0.11
    crements
    0.11
     Increment
    0.11
    _INCREMENT
    0.10
    .increment
    0.10
    Activations Density 0.007%

    No Known Activations