© 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. 18291
    Prev
    Next
    INDEX
    Explanations

    Quadrants

    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
     هر
    -0.10
     cada
    -0.09
    另
    -0.09
     isang
    -0.09
    ضير
    -0.09
     peruste
    -0.08
     beneficia
    -0.08
    bagai
    -0.08
    ටි
    -0.08
     seluruh
    -0.08
    POSITIVE LOGITS
    _Position
    0.09
    _Error
    0.08
    _NEG
    0.08
    Diagonal
    0.08
     Negative
    0.08
    _Invalid
    0.08
    _ERROR
    0.07
    _Mod
    0.07
    .Debug
    0.07
     Knowledge
    0.07
    Activations Density 0.008%

    No Known Activations