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. 49271
    Prev
    Next
    INDEX
    Explanations

    long division

    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
    developers
    -0.09
    disposed
    -0.08
    群
    -0.08
    joined
    -0.08
    edido
    -0.08
     sumus
    -0.08
    tracked
    -0.08
    relationship
    -0.08
     partying
    -0.07
     quantified
    -0.07
    POSITIVE LOGITS
     manually
    0.10
     workings
    0.09
     вруч
    0.09
     Manual
    0.08
     Towers
    0.08
    Manual
    0.08
     manual
    0.08
     النقد
    0.08
     algorithms
    0.08
     algorithm
    0.08
    Activations Density 0.017%

    No Known Activations