© 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. 23-RESID-POST-AA
    11. 49671
    Prev
    Next
    INDEX
    Explanations

    "I" in different languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     my
    -0.13
     our
    -0.13
     you've
    -0.11
     you'd
    -0.10
     we've
    -0.10
     våra
    -0.10
    (my
    -0.10
     it
    -0.10
     we'd
    -0.10
     vores
    -0.09
    POSITIVE LOGITS
     أنا
    0.29
    أنا
    0.29
     jestem
    0.26
     Я
    0.25
     אני
    0.25
    אני
    0.24
    मैं
    0.24
    Я
    0.24
     मैं
    0.23
     હું
    0.23
    Activations Density 0.058%

    No Known Activations