© 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. 21960
    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
     Its
    -0.23
     its
    -0.23
    Its
    -0.22
     itself
    -0.19
     उसे
    -0.19
     jego
    -0.19
     jeho
    -0.19
     उसका
    -0.19
     ఉంది
    -0.19
     його
    -0.18
    POSITIVE LOGITS
     themselves
    0.39
     their
    0.34
     Their
    0.32
    Their
    0.32
     իրենց
    0.31
     তাদের
    0.31
    their
    0.31
     അവരുടെ
    0.30
     شوند
    0.30
     తమ
    0.30
    Activations Density 1.549%

    No Known Activations