© 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. 48176
    Prev
    Next
    INDEX
    Explanations

    code

    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
     code
    -0.11
    代码
    -0.10
    Code
    -0.09
     código
    -0.09
    _code
    -0.09
    コード
    -0.09
    _CODE
    -0.09
     kode
    -0.09
    �்
    -0.09
     Code
    -0.09
    POSITIVE LOGITS
    forces
    0.22
    pendency
    0.21
    base
    0.21
    book
    0.20
    pendent
    0.20
     snippet
    0.20
    books
    0.18
    words
    0.18
    word
    0.18
    bases
    0.17
    Activations Density 0.050%

    No Known Activations