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. 15-RESID-POST-AA
    6. 19482
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
     these
    -0.10
    ce
    -0.08
    ,"
    -0.08
    these
    -0.08
     interpersonal
    -0.08
    These
    -0.07
    ",[
    -0.07
     与
    -0.07
    יבי
    -0.07
     These
    -0.07
    POSITIVE LOGITS
     Alguns
    0.10
    ။↵↵
    0.09
     bazı
    0.09
     Einige
    0.09
     काही
    0.09
    ។↵↵
    0.09
     Algunos
    0.09
     ڪجهه
    0.09
     કેટલાક
    0.09
     ചില
    0.08
    Activations Density 0.019%

    No Known Activations