© 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. 54872
    Prev
    Next
    INDEX
    Explanations

    sum

    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
     Cous
    -0.08
    Wall
    -0.08
     Wall
    -0.08
     стены
    -0.07
     Conditioning
    -0.07
     FRONT
    -0.07
    192
    -0.07
     Tyler
    -0.07
     Carlton
    -0.07
    _wall
    -0.07
    POSITIVE LOGITS
    关于
    0.09
     parlé
    0.09
     traduz
    0.08
     أخبار
    0.08
     sagen
    0.08
     इं
    0.08
    টা
    0.07
     sno
    0.07
    执行
    0.07
    珍
    0.07
    Activations Density 0.012%

    No Known Activations