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. 44149
    Prev
    Next
    INDEX
    Explanations

    Non-English text

    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
     vaping
    -0.08
     Drog
    -0.08
     combinatie
    -0.07
    ansett
    -0.07
     mavjud
    -0.07
     Paul's
    -0.07
     encontra
    -0.07
     “[
    -0.07
     Pharmaceuticals
    -0.07
     Michael
    -0.07
    POSITIVE LOGITS
     subsidiary
    0.13
     concrete
    0.11
     smaller
    0.11
     practical
    0.11
     secondary
    0.10
     subordinate
    0.10
     sub
    0.10
     auxiliary
    0.10
    secondary
    0.10
     technical
    0.09
    Activations Density 0.027%

    No Known Activations