© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 51909
    Prev
    Next
    INDEX
    Explanations

    likely Tagalog

    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
     aug
    -0.08
     agenda
    -0.08
     һә
    -0.08
    humela
    -0.08
    agenda
    -0.07
     हामी
    -0.07
     υ
    -0.07
     رهيو
    -0.07
    Aug
    -0.07
    Azur
    -0.07
    POSITIVE LOGITS
     regression
    0.08
    Regression
    0.08
    Voor
    0.07
     Regression
    0.07
    ò
    0.07
     reisen
    0.07
    ặt
    0.07
     regres
    0.07
    òp
    0.07
     regress
    0.07
    Activations Density 0.001%

    No Known Activations