© 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. 67
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    avio
    -0.08
     jakie
    -0.08
     Ottoman
    -0.08
    incl
    -0.08
    elateerde
    -0.07
     survivors
    -0.07
     termasuk
    -0.07
     обзор
    -0.07
    were
    -0.07
     demeanor
    -0.07
    POSITIVE LOGITS
    绑定
    0.09
    授
    0.09
    (bind
    0.08
    绑
    0.08
     drain
    0.08
    赋
    0.08
    |(
    0.08
     exclusiva
    0.08
     condicion
    0.08
     feeding
    0.08
    Activations Density 0.003%

    No Known Activations