© 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. 23-RESID-POST-AA
    11. 51212
    Prev
    Next
    INDEX
    Explanations

    sum

    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
     волос
    -0.08
     době
    -0.08
     волосы
    -0.08
     χώ
    -0.08
     жоғ
    -0.08
    iehlt
    -0.08
     обеспеч
    -0.08
     העבודה
    -0.08
    рем
    -0.08
    βου
    -0.07
    POSITIVE LOGITS
     involving
    0.17
     envolvendo
    0.13
     landscape
    0.10
    ഒരു
    0.10
     가능한
    0.10
     ഒരു
    0.09
     unui
    0.09
     Landscape
    0.09
     لأي
    0.09
     achievable
    0.09
    Activations Density 0.085%

    No Known Activations