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. 77590
    Prev
    Next
    INDEX
    Explanations

    abolition

    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
     SEO
    -0.08
     Stadium
    -0.07
     Salv
    -0.07
     Specifically
    -0.07
     बार
    -0.07
    /pkg
    -0.07
     camer
    -0.07
     अवसर
    -0.07
    pkg
    -0.07
    _OC
    -0.07
    POSITIVE LOGITS
     abolition
    0.11
     abolished
    0.11
     abol
    0.11
     slavery
    0.10
     throat
    0.09
    allist
    0.09
    慈
    0.08
     levy
    0.08
     cigarette
    0.08
     Lenn
    0.08
    Activations Density 0.005%

    No Known Activations