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. 11-RESID-POST-AA
    6. 54010
    Prev
    Next
    INDEX
    Explanations

    descriptive

    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
     Tempor
    -0.08
     respite
    -0.08
     tempor
    -0.08
     Temporal
    -0.08
     hotspots
    -0.07
     hotspot
    -0.07
    痛
    -0.07
    :this
    -0.07
     Temporary
    -0.07
     turns
    -0.07
    POSITIVE LOGITS
     ann
    0.07
     المطلوبة
    0.07
     dài
    0.07
    RSS
    0.07
     ez
    0.07
     목표
    0.07
     lema
    0.07
    lela
    0.07
     والط
    0.07
    Ә
    0.07
    Activations Density 0.001%

    No Known Activations