© 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. 65012
    Prev
    Next
    INDEX
    Explanations

    Chinese language

    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
     मिस
    -0.08
     acquisition
    -0.08
     host
    -0.08
     feeder
    -0.07
     эксп
    -0.07
     easiest
    -0.07
     plat
    -0.07
    plex
    -0.07
    plat
    -0.07
     Acquisition
    -0.07
    POSITIVE LOGITS
     debo
    0.09
     ਮੇ
    0.08
    Forgot
    0.08
    ਿੰਦ
    0.08
    Fl
    0.08
    Fal
    0.08
    ucci
    0.08
    奋
    0.08
    Meine
    0.08
     Ma
    0.08
    Activations Density 0.015%

    No Known Activations