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. 11-RESID-POST-AA
    6. 90101
    Prev
    Next
    INDEX
    Explanations

    all

    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
     താമ
    -0.08
     مث
    -0.08
     Unterkunft
    -0.08
     pokuš
    -0.08
     Mattress
    -0.08
    _ray
    -0.08
     kasar
    -0.08
     ориент
    -0.08
    住宿
    -0.07
     Mosaic
    -0.07
    POSITIVE LOGITS
     equality
    0.08
     chromatography
    0.08
    成立
    0.08
     Dummy
    0.07
    167
    0.07
     unveiling
    0.07
    .$$
    0.07
    验证
    0.07
    ynomial
    0.07
     contradiction
    0.07
    Activations Density 0.031%

    No Known Activations