© 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. 23-RESID-POST-AA
    11. 50352
    Prev
    Next
    INDEX
    Explanations

    say "ج"

    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
     Häuser
    -0.08
    ெய
    -0.08
     bod
    -0.08
    enting
    -0.07
    ent
    -0.07
    andr
    -0.07
     house
    -0.07
     weiteres
    -0.07
     cet
    -0.07
    ib
    -0.07
    POSITIVE LOGITS
    ّد
    0.10
    ج
    0.10
    ّ
    0.09
    ّر
    0.09
    ِّ
    0.09
    ّن
    0.09
     шак
    0.09
    ّل
    0.08
    ади
    0.08
    ّه
    0.08
    Activations Density 0.000%

    No Known Activations