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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 26084
    Prev
    Next
    INDEX
    Explanations

    expository writing

    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
     Libert
    -0.09
     matern
    -0.08
     Rp
    -0.08
     cages
    -0.08
     Pods
    -0.08
     payload
    -0.07
    _PIN
    -0.07
     NVIDIA
    -0.07
     cage
    -0.07
    Payload
    -0.07
    POSITIVE LOGITS
     nonfiction
    0.10
    专题
    0.09
     argumentative
    0.09
    문
    0.09
    Arrangement
    0.09
    -style
    0.08
     encyclopedia
    0.08
     introductory
    0.08
    作文
    0.08
     rhetorical
    0.08
    Activations Density 0.027%

    No Known Activations