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. 29891
    Prev
    Next
    INDEX
    Explanations

    literary texts

    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
    Rewards
    -0.08
     grunt
    -0.07
     Michigan
    -0.07
     search
    -0.07
    ông
    -0.07
     Sis
    -0.07
     folders
    -0.07
     mito
    -0.07
     MSI
    -0.07
    adoop
    -0.07
    POSITIVE LOGITS
     Fabian
    0.09
    _CONTROLLER
    0.09
     myster
    0.09
     odborn
    0.08
    (active
    0.08
     fflush
    0.08
     زد
    0.08
     speziellen
    0.08
    =str
    0.08
     vormt
    0.08
    Activations Density 0.001%

    No Known Activations