© 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. 20150
    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
    它
    -0.10
     They
    -0.09
     அது
    -0.09
     It
    -0.09
     it
    -0.09
     zuerst
    -0.09
     они
    -0.09
     catchy
    -0.08
     they're
    -0.08
     they
    -0.08
    POSITIVE LOGITS
    Responsibilities
    0.13
    职责
    0.10
     responsibilities
    0.09
     Responsibilities
    0.09
     المسؤول
    0.09
     विशेषज्ञ
    0.09
     responsabilidades
    0.09
     जिम्म
    0.09
     verantwoordelijk
    0.09
    ████
    0.09
    Activations Density 0.004%

    No Known Activations