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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44133
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    小学
    -0.09
    大众
    -0.08
    驶
    -0.08
    ピ
    -0.08
     savvy
    -0.08
    稍
    -0.08
     Wörter
    -0.08
    靠
    -0.08
    动态
    -0.07
    _DYNAMIC
    -0.07
    POSITIVE LOGITS
     generator
    0.09
    .transpose
    0.09
    .mul
    0.09
    igs
    0.08
     mul
    0.08
     доказ
    0.08
    ulnerability
    0.08
     produire
    0.08
     conv
    0.08
     MUL
    0.08
    Activations Density 0.000%

    No Known Activations