© 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. 22344
    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
    धर
    -0.08
     المسلحة
    -0.07
    елю
    -0.07
    vari
    -0.07
     any
    -0.07
     knowledgeable
    -0.07
    ional
    -0.07
     significant
    -0.07
     salient
    -0.07
    มัน
    -0.07
    POSITIVE LOGITS
    慎
    0.12
    阅
    0.11
    査
    0.11
    isaties
    0.10
    查
    0.10
    ிக்கை
    0.09
    íos
    0.09
    iencias
    0.09
    erende
    0.09
    isasi
    0.09
    Activations Density 0.001%

    No Known Activations