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. 52946
    Prev
    Next
    INDEX
    Explanations

    ).^

    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
    вай
    -0.07
     ett
    -0.07
    rit
    -0.07
    ایک
    -0.07
    સાર
    -0.07
    illiams
    -0.07
    urses
    -0.07
    ਯ
    -0.07
     stool
    -0.07
    uir
    -0.07
    POSITIVE LOGITS
     rebates
    0.09
     nghi
    0.08
     exceeded
    0.08
    objs
    0.08
     heridas
    0.08
    ARRAY
    0.08
     Wherever
    0.08
     bất
    0.08
    ან
    0.08
     prevenir
    0.07
    Activations Density 0.009%

    No Known Activations