© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30942
    Prev
    Next
    INDEX
    Explanations

    thread

    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
     sann
    -0.08
     priorities
    -0.08
     quantities
    -0.08
    -def
    -0.08
    �
    -0.08
    优
    -0.07
    gmail
    -0.07
    ois
    -0.07
     concentrations
    -0.07
     seep
    -0.07
    POSITIVE LOGITS
     Dew
    0.08
     Technik
    0.07
     Indigo
    0.07
     Hobby
    0.07
    (named
    0.07
     sourcing
    0.07
    _ENGINE
    0.07
    ತ
    0.07
    ಾಲಯ
    0.07
     Named
    0.07
    Activations Density 0.001%

    No Known Activations