© 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. 18747
    Prev
    Next
    INDEX
    Explanations

    we

    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
     assigning
    -0.09
     assign
    -0.08
     notion
    -0.08
     "
    -0.08
     assigns
    -0.07
    Associate
    -0.07
     marking
    -0.07
     associ
    -0.07
    associate
    -0.07
    Assign
    -0.07
    POSITIVE LOGITS
     potřeb
    0.15
     kailangan
    0.14
     needed
    0.14
     cần
    0.14
     кирәк
    0.14
     نیاز
    0.14
     патрэ
    0.14
    _needed
    0.14
     bezwen
    0.13
     تحتاج
    0.13
    Activations Density 0.031%

    No Known Activations