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

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 19270
    Prev
    Next
    INDEX
    Explanations

    +

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    قاذ
    -0.08
    、有
    -0.08
    、新
    -0.08
    elend
    -0.08
    乃
    -0.08
     reconhe
    -0.08
     perdere
    -0.08
     ulag
    -0.08
    ките
    -0.08
    、それ
    -0.08
    POSITIVE LOGITS
     with
    0.08
     blurry
    0.08
     this
    0.07
    (strategy
    0.07
     brainstorm
    0.07
     one
    0.07
    with
    0.07
    -songwriter
    0.07
     for
    0.07
     that
    0.07
    Activations Density 0.006%

    No Known Activations