© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 48934
    Prev
    Next
    INDEX
    Explanations

    Iran locations

    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
    ød
    -0.09
     AML
    -0.08
    .functional
    -0.08
    ivée
    -0.08
    ppi
    -0.08
    tty
    -0.08
    िद
    -0.08
    sø
    -0.08
    äub
    -0.08
    emma
    -0.08
    POSITIVE LOGITS
     بلوچستان
    0.13
     کو
    0.12
     کرد
    0.12
     Bus
    0.12
     Is
    0.11
     Dez
    0.11
     Das
    0.11
     Horm
    0.11
     رشته
    0.11
     Bandar
    0.11
    Activations Density 0.007%

    No Known Activations