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. 61277
    Prev
    Next
    INDEX
    Explanations

    numbers in math problems

    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
    和值
    -0.08
     disciplina
    -0.08
     spelling
    -0.07
     discipline
    -0.07
     República
    -0.07
    Latin
    -0.07
    ails
    -0.07
     grammar
    -0.07
     شان
    -0.07
    Busca
    -0.07
    POSITIVE LOGITS
    ビー
    0.08
     sheer
    0.08
     nascer
    0.08
     quantify
    0.08
     knockout
    0.07
     hybride
    0.07
     hybr
    0.07
     intox
    0.07
    	count
    0.07
     Blogging
    0.07
    Activations Density 0.028%

    No Known Activations