© 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. 18974
    Prev
    Next
    INDEX
    Explanations

    can

    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
     ihtiyaç
    -0.10
    حتاج
    -0.10
     necesita
    -0.09
     пыта
    -0.09
     להתמודד
    -0.09
     planificación
    -0.09
     bisogno
    -0.09
     bezwen
    -0.09
     capire
    -0.09
     মোক
    -0.09
    POSITIVE LOGITS
     mention
    0.26
     Mention
    0.21
     mentioning
    0.21
     mencionar
    0.20
     mentions
    0.19
    mention
    0.19
    Mention
    0.19
     ذکر
    0.19
     stating
    0.18
     note
    0.18
    Activations Density 0.052%

    No Known Activations