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. 87983
    Prev
    Next
    INDEX
    Explanations

    Big data

    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
     Webster
    -0.09
     Wallace
    -0.08
    -0.08
     Muskel
    -0.07
     Keto
    -0.07
     Klar
    -0.07
    CLC
    -0.07
     mediante
    -0.07
     chargé
    -0.07
    \Exception
    -0.07
    POSITIVE LOGITS
     complexity
    0.12
     Complexity
    0.11
     heter
    0.10
     heterogeneous
    0.10
    heter
    0.10
     unpredict
    0.10
     разнообраз
    0.10
     dimensional
    0.09
     irregular
    0.09
    复杂
    0.09
    Activations Density 0.012%

    No Known Activations