© 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. 97356
    Prev
    Next
    INDEX
    Explanations

    say 13

    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
     თვით
    -0.09
    رياض
    -0.09
     welaýat
    -0.09
     თბილის
    -0.09
     Vital
    -0.09
     Тоҷикистон
    -0.09
    Vital
    -0.09
     frau
    -0.09
     žena
    -0.08
    ätä
    -0.08
    POSITIVE LOGITS
    13
    0.20
    ۱۳
    0.16
    १३
    0.15
    １３
    0.14
    ১৩
    0.12
    irteen
    0.11
    十三
    0.09
    ૧�
    0.09
     thirteen
    0.09
    130
    0.08
    Activations Density 0.068%

    No Known Activations