© 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. 18790
    Prev
    Next
    INDEX
    Explanations

    Months (numerical)

    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
    .REG
    -0.09
    .А
    -0.08
    .(
    -0.08
    .М
    -0.08
    .G
    -0.08
    .Г
    -0.08
    Provider
    -0.08
    До
    -0.08
    .B
    -0.08
     spécifiques
    -0.08
    POSITIVE LOGITS
    08
    0.14
    07
    0.14
    09
    0.13
    04
    0.13
    03
    0.13
    05
    0.13
    06
    0.12
    02
    0.12
    01
    0.11
     december
    0.09
    Activations Density 0.002%

    No Known Activations