© 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. 110603
    Prev
    Next
    INDEX
    Explanations

    double

    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
     invol
    -0.08
    yo
    -0.08
     externally
    -0.08
     imp
    -0.07
    nelles
    -0.07
    mtime
    -0.07
    �
    -0.07
    ğlu
    -0.07
    394
    -0.07
    liness
    -0.07
    POSITIVE LOGITS
    -thirds
    0.10
     entw
    0.08
     shirts
    0.08
     मो
    0.08
    აგ
    0.08
     વખત
    0.08
     Crunch
    0.08
     champ
    0.07
     бра
    0.07
     capa
    0.07
    Activations Density 0.022%

    No Known Activations