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. 8674
    Prev
    Next
    INDEX
    Explanations

    unwanted romantic advances

    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
    .ejb
    -0.08
     Valve
    -0.08
     Coul
    -0.08
     ресурс
    -0.08
     kø
    -0.07
     azok
    -0.07
    -ending
    -0.07
     Elektro
    -0.07
     самим
    -0.07
     Faucet
    -0.07
    POSITIVE LOGITS
     stevig
    0.09
    floor
    0.08
    дин
    0.08
    keurig
    0.08
    疯
    0.08
    учу
    0.08
     tido
    0.08
     wildly
    0.07
    녀
    0.07
     batalha
    0.07
    Activations Density 0.003%

    No Known Activations