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. 130407
    Prev
    Next
    INDEX
    Explanations

    m

    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
     directions
    -0.08
     Interpret
    -0.08
    ferences
    -0.08
    cedence
    -0.07
     برخ
    -0.07
     Holding
    -0.07
    ferenz
    -0.07
     Lal
    -0.07
    Interpret
    -0.07
     Azi
    -0.07
    POSITIVE LOGITS
    .mkdir
    0.09
    .create
    0.09
    .mkdirs
    0.08
     mkdir
    0.08
     创建
    0.08
    .makedirs
    0.08
    创建
    0.08
    #w
    0.08
    開始
    0.08
    ライ
    0.08
    Activations Density 0.001%

    No Known Activations