© 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. 19883
    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
     সমস্ত
    -0.10
    parts
    -0.09
     všet
    -0.09
     seluruh
    -0.09
     সকল
    -0.09
    include
    -0.09
     entirety
    -0.09
     wszystkich
    -0.09
     అన్ని
    -0.09
     semua
    -0.09
    POSITIVE LOGITS
     the
    0.11
     spectrum
    0.10
     that
    0.10
     که
    0.10
     जिसे
    0.09
     which
    0.08
    pectrum
    0.08
     it
    0.08
     который
    0.08
    ’histoire
    0.08
    Activations Density 0.053%

    No Known Activations