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. 112944
    Prev
    Next
    INDEX
    Explanations

    Punctuation and conjunctions

    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
     hetzelfde
    -0.09
    Ticker
    -0.08
    овых
    -0.08
     rasmi
    -0.08
    овой
    -0.08
    ового
    -0.08
    宗
    -0.08
     vanaf
    -0.08
     unbedingt
    -0.07
    وامل
    -0.07
    POSITIVE LOGITS
    无法
    0.10
     inability
    0.10
     headaches
    0.10
     vorz
    0.10
     falta
    0.09
     unrealistic
    0.09
     ansiedad
    0.08
     dificultad
    0.08
     decreased
    0.08
     difficulties
    0.08
    Activations Density 0.059%

    No Known Activations