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. 112143
    Prev
    Next
    INDEX
    Explanations

    Song structure

    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
     taht
    -0.08
     absolute
    -0.07
     Malta
    -0.07
    ugues
    -0.07
     linear
    -0.07
     Turkey
    -0.07
     additive
    -0.07
     France
    -0.07
     Spain
    -0.07
     cupboard
    -0.07
    POSITIVE LOGITS
     novamente
    0.11
     nuevamente
    0.11
     снова
    0.11
    again
    0.10
     опять
    0.10
     erneut
    0.10
     Again
    0.10
    再次
    0.10
     again
    0.09
    Again
    0.09
    Activations Density 0.011%

    No Known Activations