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. 65702
    Prev
    Next
    INDEX
    Explanations

    crime fiction

    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
     trés
    -0.08
    रों
    -0.08
    梅
    -0.08
    ਟੀ
    -0.08
     FL
    -0.08
    ARSE
    -0.07
    plies
    -0.07
     inspect
    -0.07
    �
    -0.07
    /program
    -0.07
    POSITIVE LOGITS
     måske
    0.08
     Sic
    0.08
     reportedly
    0.07
     використов
    0.07
     Somehow
    0.07
     Elegant
    0.07
     supposedly
    0.07
     strangely
    0.07
    Elegant
    0.07
     Apparently
    0.07
    Activations Density 0.010%

    No Known Activations