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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 58892
    Prev
    Next
    INDEX
    Explanations

    investment payback

    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
     descendant
    -0.08
     imperson
    -0.08
     Sunday's
    -0.07
    unday
    -0.07
     ancestors
    -0.07
    andag
    -0.07
     grupper
    -0.07
     Unicode
    -0.07
     그룹
    -0.07
    clipboard
    -0.07
    POSITIVE LOGITS
    几年
    0.11
    期间
    0.10
     savings
    0.09
     ચુક
    0.09
     થયો
    0.09
    Saving
    0.09
    预计
    0.09
    Startup
    0.09
     gypsum
    0.08
     takaisin
    0.08
    Activations Density 0.010%

    No Known Activations