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. 15-RESID-POST-AA
    6. 19346
    Prev
    Next
    INDEX
    Explanations

    reuse

    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
    instagram
    -0.08
     విచ
    -0.07
    itiko
    -0.07
     desapare
    -0.07
    ిని
    -0.07
     followed
    -0.07
     విషయం
    -0.07
    좌
    -0.07
     instagram
    -0.07
     desapar
    -0.07
    POSITIVE LOGITS
     reuse
    0.18
     reutil
    0.16
     reused
    0.15
     reusable
    0.15
    Reusable
    0.14
    Reuse
    0.14
    reuse
    0.12
     across
    0.10
    Across
    0.10
    利用
    0.09
    Activations Density 0.010%

    No Known Activations