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

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 138
    Prev
    Next
    INDEX
    Explanations

    launch

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canterbury
    -0.08
    िना
    -0.08
    ено
    -0.08
    ичество
    -0.07
    ажно
    -0.07
    ларда
    -0.07
    ują
    -0.07
     आदेश
    -0.07
    _UNKNOWN
    -0.07
    কারী
    -0.07
    POSITIVE LOGITS
     출시
    0.13
     aimed
    0.11
    推出
    0.11
     लॉन्च
    0.11
     അവതരിപ്പ
    0.10
     રજૂ
    0.10
     premiered
    0.10
     lancement
    0.10
     launched
    0.10
     unveiled
    0.10
    Activations Density 0.152%

    No Known Activations