© 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. 22267
    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
    нодар
    -0.12
     જિલ્લામાં
    -0.11
     mpaghara
    -0.11
    ിയിലെ
    -0.11
     pagbaba
    -0.11
     ജില്ലയിലെ
    -0.11
     deltag
    -0.10
    nhof
    -0.10
     ndalama
    -0.10
     જિલ્લાના
    -0.10
    POSITIVE LOGITS
     true
    0.23
    _TRUE
    0.21
     TRUE
    0.21
    true
    0.20
    _true
    0.20
    True
    0.20
    >true
    0.20
     True
    0.19
    :true
    0.19
    .True
    0.19
    Activations Density 0.029%

    No Known Activations