© 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. 78399
    Prev
    Next
    INDEX
    Explanations

    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
     counc
    -0.08
    (interface
    -0.07
     Coun
    -0.07
     Rast
    -0.07
     સામ
    -0.07
    aed
    -0.07
     incul
    -0.07
     Ital
    -0.07
     stains
    -0.07
     Johan
    -0.07
    POSITIVE LOGITS
    “To
    0.09
     transform
    0.09
    发行
    0.09
     schwe
    0.09
    akkat
    0.09
    广播
    0.09
    发布时间
    0.09
    >((
    0.08
    nehmer
    0.08
     gé
    0.08
    Activations Density 0.002%

    No Known Activations