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. 48801
    Prev
    Next
    INDEX
    Explanations

    financial contributions

    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
     nerd
    -0.08
     plumber
    -0.08
     agr
    -0.08
     show
    -0.07
     equipped
    -0.07
     librarian
    -0.07
    glyph
    -0.07
    agr
    -0.07
     Running
    -0.07
     visual
    -0.07
    POSITIVE LOGITS
     supplementation
    0.15
     supplemented
    0.14
     ergän
    0.12
     supplements
    0.12
     aanvull
    0.11
     contributions
    0.11
     supplementary
    0.11
     Supplements
    0.11
    补
    0.11
     supplemental
    0.11
    Activations Density 0.038%

    No Known Activations