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. 19578
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
     době
    -0.08
    民
    -0.08
    	DBG
    -0.08
     semanas
    -0.08
     Detailed
    -0.08
     estime
    -0.08
     intuit
    -0.07
    Dbg
    -0.07
    schap
    -0.07
    .Database
    -0.07
    POSITIVE LOGITS
     punctuation
    0.13
     commas
    0.13
    Comma
    0.12
     comma
    0.12
    comma
    0.11
     запрещ
    0.11
    禁止
    0.11
     alphabetical
    0.10
    は禁止
    0.10
    alphabet
    0.10
    Activations Density 0.002%

    No Known Activations