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. 112868
    Prev
    Next
    INDEX
    Explanations

    memorable experiences

    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
    dere
    -0.08
     rundown
    -0.08
     botón
    -0.08
     شتون
    -0.08
     Intelligence
    -0.08
    -employed
    -0.08
     tasa
    -0.08
     feeds
    -0.07
     সুবিধ
    -0.07
    ทดลอง
    -0.07
    POSITIVE LOGITS
     unforgettable
    0.16
     memorable
    0.15
     inol
    0.13
     memories
    0.12
     forever
    0.11
     recuerdos
    0.11
    forgettable
    0.10
     memor
    0.10
     remembered
    0.10
    铭
    0.10
    Activations Density 0.040%

    No Known Activations