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. 56258
    Prev
    Next
    INDEX
    Explanations

    Servants

    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
    刺激
    -0.09
     Ark
    -0.08
     julka
    -0.08
     reun
    -0.08
     atlas
    -0.07
    _VALID
    -0.07
     provin
    -0.07
     uniqu
    -0.07
     portfolios
    -0.07
    arang
    -0.07
    POSITIVE LOGITS
     maid
    0.11
     servants
    0.11
     servant
    0.09
    佣
    0.09
     subsidiary
    0.09
     Küchen
    0.09
    .down
    0.09
     yemek
    0.08
     ensl
    0.08
     domést
    0.08
    Activations Density 0.025%

    No Known Activations