© 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. 11-RESID-POST-AA
    11. 69862
    Prev
    Next
    INDEX
    Explanations

    paths between points

    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
     oysters
    -0.09
    Valores
    -0.08
     giveaways
    -0.08
     சமூக
    -0.08
    케팅
    -0.08
    ارہ
    -0.08
    ادن
    -0.08
    focus
    -0.07
     philanthropic
    -0.07
     distributions
    -0.07
    POSITIVE LOGITS
     paths
    0.19
     পথ
    0.18
     مسیر
    0.18
    路径
    0.18
    _paths
    0.17
     Paths
    0.17
     маршру
    0.17
     маршрут
    0.17
    路线
    0.17
    Paths
    0.17
    Activations Density 0.027%

    No Known Activations