© 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 EvalsExportsAPI 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. 19789
    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
     enfoque
    -0.08
     fokus
    -0.08
    र्ड
    -0.07
     Fokus
    -0.07
    র্ড
    -0.07
     foco
    -0.07
     egiten
    -0.07
     Už
    -0.07
     Hercegov
    -0.07
    -operative
    -0.07
    POSITIVE LOGITS
    cenario
    0.19
    caling
    0.18
    hape
    0.18
    pread
    0.17
    cale
    0.17
    cene
    0.16
    hadow
    0.16
    h
    0.16
    hift
    0.16
    paces
    0.16
    Activations Density 0.067%

    No Known Activations