© 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. 19666
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    -on
    -0.08
    (init
    -0.08
    -before
    -0.08
    ishment
    -0.08
    jection
    -0.08
    JECTION
    -0.08
    (fetch
    -0.08
     عالي
    -0.08
    posals
    -0.08
    ્ચ
    -0.08
    POSITIVE LOGITS
     വൈസ്
    0.09
    anlagen
    0.09
    but
    0.09
    isul
    0.09
    maktadır
    0.09
     pair
    0.09
     paire
    0.09
     maeneo
    0.09
     koning
    0.08
    m
    0.08
    Activations Density 0.002%

    No Known Activations