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. 9272
    Prev
    Next
    INDEX
    Explanations

    Generating lists of words

    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
     organizations
    -0.08
    Organizations
    -0.08
     raka
    -0.08
     organizações
    -0.08
    _latest
    -0.08
     Dyson
    -0.08
    Driven
    -0.08
    .routes
    -0.08
     تت
    -0.08
     Watts
    -0.08
    POSITIVE LOGITS
     vowels
    0.14
     lexical
    0.14
     vowel
    0.13
     alphabetical
    0.13
     alphabet
    0.12
    词
    0.12
     vocabulary
    0.12
     conson
    0.12
    詞
    0.12
     spelling
    0.12
    Activations Density 0.038%

    No Known Activations