© 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. 19179
    Prev
    Next
    INDEX
    Explanations

    Geometry

    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
     its
    -0.10
     ένα
    -0.10
     μια
    -0.09
     επίσης
    -0.09
     their
    -0.09
     along
    -0.09
     καθη
    -0.09
     απ
    -0.09
     Its
    -0.09
     έχει
    -0.08
    POSITIVE LOGITS
    .Disable
    0.09
    .uid
    0.08
    .Raw
    0.08
    ніш
    0.08
    .CONFIG
    0.08
    급
    0.08
    Mongo
    0.08
    小时前
    0.08
    .Focus
    0.08
    ша
    0.08
    Activations Density 0.015%

    No Known Activations