Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 18755
    Prev
    Next
    INDEX
    Explanations

    mathematical statements

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .component
    -0.08
    テーマ
    -0.08
    Form
    -0.08
    してください
    -0.08
    Soll
    -0.08
    Can
    -0.08
    crypt
    -0.07
    Please
    -0.07
    forma
    -0.07
    Should
    -0.07
    POSITIVE LOGITS
     devient
    0.09
    来越
    0.09
    므로
    0.09
     poveć
    0.09
     becomes
    0.09
     níos
    0.09
     waardoor
    0.09
     соответственно
    0.09
     fogo
    0.09
     inadequate
    0.09
    Activations Density 0.061%

    No Known Activations