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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 97391
    Prev
    Next
    INDEX
    Explanations

    Arabic text

    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
    lief
    -0.08
    reatment
    -0.08
    _pan
    -0.08
    verg
    -0.08
    ात्र
    -0.08
     प्रभ
    -0.07
     clin
    -0.07
     Вал
    -0.07
    ussels
    -0.07
    ız
    -0.07
    POSITIVE LOGITS
    ارب
    0.09
    ardo
    0.09
    నలు
    0.09
    ارى
    0.08
    ابية
    0.08
    ובים
    0.08
    ود
    0.08
    odas
    0.08
    ારમાં
    0.08
     Script
    0.07
    Activations Density 0.001%

    No Known Activations