© 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. 23-RESID-POST-AA
    11. 49455
    Prev
    Next
    INDEX
    Explanations

    regression

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bouquet
    -0.10
     amic
    -0.10
     labyrinth
    -0.09
     puzzles
    -0.09
     palindrome
    -0.09
     necklaces
    -0.09
     portals
    -0.09
     domino
    -0.09
     delic
    -0.09
    Palindrome
    -0.08
    POSITIVE LOGITS
     regression
    0.33
     Regression
    0.29
    Regression
    0.29
     fitted
    0.26
     regress
    0.24
     predictor
    0.23
     predicted
    0.23
     regres
    0.23
     predictors
    0.23
    .predict
    0.23
    Activations Density 0.077%

    No Known Activations