© 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. 49275
    Prev
    Next
    INDEX
    Explanations

    say "ج" words

    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
    ators
    -0.09
    ifiés
    -0.09
     приобр
    -0.08
    apses
    -0.08
    órico
    -0.08
    óricos
    -0.08
    otherap
    -0.08
    ori
    -0.08
    ibilities
    -0.08
    ങ്ങളെ
    -0.08
    POSITIVE LOGITS
     کردن
    0.14
    ائڻ
    0.12
     دادن
    0.12
     ڪرڻ
    0.12
    ровать
    0.11
     кардани
    0.11
    ләү
    0.11
    ить
    0.11
    ுதல்
    0.11
    ивать
    0.11
    Activations Density 0.004%

    No Known Activations