© 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. 18826
    Prev
    Next
    INDEX
    Explanations

    foreign languages/code

    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
    description
    -0.11
     qhia
    -0.10
    #ae
    -0.10
    #ab
    -0.10
    ’article
    -0.10
    ’ın
    -0.10
     بررسی
    -0.10
    analysis
    -0.10
     description
    -0.10
     Analysis
    -0.09
    POSITIVE LOGITS
    ੂ
    0.14
    ୁ
    0.14
    ुवार
    0.12
    ુ
    0.12
    უ
    0.12
    ุป
    0.12
    ū
    0.11
    uose
    0.11
    ుతో
    0.11
    ু
    0.11
    Activations Density 0.720%

    No Known Activations