© 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. 19-RESID-POST-AA
    11. 102871
    Prev
    Next
    INDEX
    Explanations

    在

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     λίγο
    -0.09
     такую
    -0.09
     muligt
    -0.09
     möglich
    -0.08
    _possible
    -0.08
     եթե
    -0.08
    անալ
    -0.08
     afirmó
    -0.08
     адзнач
    -0.08
     لږ
    -0.08
    POSITIVE LOGITS
     weitem
    0.10
    整个
    0.10
    Handling
    0.10
     handling
    0.09
     kezelés
    0.09
    )의
    0.09
     Handling
    0.09
    实际上
    0.09
    ）的
    0.09
    )을
    0.09
    Activations Density 0.008%

    No Known Activations