© 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. 5992
    Prev
    Next
    INDEX
    Explanations

    Subtraction computations

    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
     �
    -0.08
    ến
    -0.08
    iseksi
    -0.08
     liên
    -0.08
     Inatsisartut
    -0.08
     الإسلامية
    -0.08
    кия
    -0.08
    isummaa
    -0.08
    الإ
    -0.08
     kunden
    -0.08
    POSITIVE LOGITS
    AFX
    0.09
    Square
    0.07
    Pix
    0.07
    trast
    0.07
    vid
    0.07
     squares
    0.07
    _;↵↵
    0.07
     ваз
    0.07
    720
    0.07
    902
    0.07
    Activations Density 0.000%

    No Known Activations