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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 54063
    Prev
    Next
    INDEX
    Explanations

    File destinations

    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
     ฉ
    -0.08
     imaginative
    -0.08
     jeder
    -0.08
    romen
    -0.08
     elimination
    -0.08
     שכל
    -0.07
     aesthetic
    -0.07
    -material
    -0.07
     progn
    -0.07
     weitere
    -0.07
    POSITIVE LOGITS
    指定
    0.10
    _LOCAL
    0.08
     지정
    0.08
     locally
    0.08
    entions
    0.08
    ोड
    0.08
    Nx
    0.08
    		        
    0.07
    Specify
    0.07
    .'.
    0.07
    Activations Density 0.004%

    No Known Activations