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. 120417
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
     incarcerated
    -0.08
    .Compiler
    -0.08
    .Restr
    -0.08
     afflicted
    -0.07
    ztat
    -0.07
    Feign
    -0.07
     redan
    -0.07
     companion
    -0.07
    омним
    -0.07
    μφ
    -0.07
    POSITIVE LOGITS
    UInt
    0.08
     UInt
    0.08
     rise
    0.08
    最大的
    0.08
     основные
    0.07
    0.07
    últ
    0.07
     XV
    0.07
     વૃ
    0.07
     כ
    0.07
    Activations Density 0.000%

    No Known Activations