Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 58480
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    _tcp
    -0.08
    _TCP
    -0.08
     POT
    -0.07
    Achievement
    -0.07
     τύ
    -0.07
    achievement
    -0.07
     тариф
    -0.07
     वाहन
    -0.07
     faci
    -0.07
     했
    -0.07
    POSITIVE LOGITS
     parsley
    0.14
     cilantro
    0.12
     herbs
    0.11
     seedlings
    0.11
     thyme
    0.10
     garnish
    0.09
     dill
    0.09
     oregano
    0.09
    ereke
    0.09
    草
    0.09
    Activations Density 0.012%

    No Known Activations