Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 76469
    Prev
    Next
    INDEX
    Explanations

    qar

    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
    .W
    -0.08
    (W
    -0.08
     MW
    -0.08
    -W
    -0.08
     WR
    -0.08
    _W
    -0.08
    Head
    -0.07
     Sle
    -0.07
    Single
    -0.07
    /W
    -0.07
    POSITIVE LOGITS
     dav
    0.09
     atoi
    0.09
     contro
    0.08
     getline
    0.08
     xpos
    0.08
     insta
    0.08
     cak
    0.08
     zalo
    0.08
     معامله
    0.08
     음
    0.08
    Activations Density 0.003%

    No Known Activations