© 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. 19-RESID-POST-AA
    11. 18328
    Prev
    Next
    INDEX
    Explanations

    can

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .This
    -0.07
     \(
    -0.07
    。据
    -0.07
     Viele
    -0.07
     Firstly
    -0.07
     −
    -0.07
    .START
    -0.07
     ****
    -0.07
    。如果
    -0.07
     (-
    -0.07
    POSITIVE LOGITS
     imaginative
    0.16
     художе
    0.15
     artistic
    0.15
     stylist
    0.13
     creative
    0.13
     focus
    0.13
     inventive
    0.13
     watercolor
    0.12
     fantasy
    0.12
     focuses
    0.12
    Activations Density 0.001%

    No Known Activations