© 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. 18562
    Prev
    Next
    INDEX
    Explanations

    blow

    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
    IMER
    -0.09
    IALOG
    -0.08
     جديدة
    -0.08
    .imgur
    -0.08
    YSTEM
    -0.08
    IM
    -0.08
    'invest
    -0.08
    ILITY
    -0.08
     מאוד
    -0.07
    新
    -0.07
    POSITIVE LOGITS
    outs
    0.10
    out
    0.10
    hole
    0.10
    -up
    0.10
    fish
    0.10
    holes
    0.09
    uenta
    0.09
    dryer
    0.09
    �西
    0.09
    -hole
    0.09
    Activations Density 0.003%

    No Known Activations