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. 157
    Prev
    Next
    INDEX
    Explanations

    valuable

    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
    Flags
    -0.07
    Effects
    -0.07
     बेल
    -0.07
     Madness
    -0.07
    Counters
    -0.07
    สาว
    -0.07
     Fleisch
    -0.07
    .shadow
    -0.07
    Sprites
    -0.07
     largest
    -0.07
    POSITIVE LOGITS
     valuable
    0.15
     콘텐츠
    0.15
     Valuable
    0.14
     полез
    0.13
     conteúdo
    0.13
    valuable
    0.12
     informative
    0.12
     sadrž
    0.12
     Inhalte
    0.12
    内容
    0.12
    Activations Density 0.042%

    No Known Activations