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. 112063
    Prev
    Next
    INDEX
    Explanations

    Instructions or constraints

    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
     Jezus
    -0.08
     negoc
    -0.08
     сан
    -0.08
     Herr
    -0.08
     časa
    -0.08
     mål
    -0.07
     Raise
    -0.07
     Lynch
    -0.07
     guer
    -0.07
     Estate
    -0.07
    POSITIVE LOGITS
     footer
    0.10
     prematurely
    0.09
     omitted
    0.09
    .Footer
    0.08
     prose
    0.08
     Footer
    0.08
    الی
    0.07
    .Inventory
    0.07
    ICIO
    0.07
     om
    0.07
    Activations Density 0.000%

    No Known Activations