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. 61028
    Prev
    Next
    INDEX
    Explanations

    software configuration

    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
     Forced
    -0.08
     средство
    -0.08
     Бу
    -0.08
     forced
    -0.08
    Forced
    -0.07
    ,截至
    -0.07
     Бал
    -0.07
     recreational
    -0.07
     Winners
    -0.07
     والح
    -0.07
    POSITIVE LOGITS
    .dep
    0.08
     dialogues
    0.07
     titt
    0.07
    篇
    0.07
     vend
    0.07
     interven
    0.07
    .absolute
    0.07
    tej
    0.07
    .style
    0.07
     impover
    0.07
    Activations Density 0.003%

    No Known Activations