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. 112659
    Prev
    Next
    INDEX
    Explanations

    Punctuation and formatting

    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
     فقد
    -0.08
    smith
    -0.08
     rech
    -0.08
     temper
    -0.08
    朝
    -0.07
     raf
    -0.07
     rein
    -0.07
    握
    -0.07
    欢乐
    -0.07
     ملت
    -0.07
    POSITIVE LOGITS
    itialize
    0.09
    uprofen
    0.09
    ialize
    0.09
    roduction
    0.09
    -магаз
    0.08
    ividual
    0.08
    quierda
    0.08
    ತ್ತೀಚ
    0.08
    порт
    0.08
    duct
    0.08
    Activations Density 0.298%

    No Known Activations