© 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. 96911
    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
     vá
    -0.10
    vá
    -0.09
     PLN
    -0.09
     ચલ
    -0.09
     NOTHING
    -0.08
    ivate
    -0.08
    ów
    -0.08
    etés
    -0.08
    ujem
    -0.08
    .props
    -0.08
    POSITIVE LOGITS
     النساء
    0.12
    هود
    0.10
     الإنسان
    0.10
    نساء
    0.10
     عمران
    0.10
     الحجر
    0.09
     المؤمن
    0.09
     Yusuf
    0.09
     An
    0.09
     الرحمن
    0.09
    Activations Density 0.001%

    No Known Activations