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. 23-RESID-POST-AA
    6. 98516
    Prev
    Next
    INDEX
    Explanations

    Google APIs and services

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vironnement
    -0.10
    quinho
    -0.08
     пози
    -0.08
    positie
    -0.08
     poem
    -0.08
    -position
    -0.08
    itong
    -0.08
    engo
    -0.08
    opuerto
    -0.08
     QB
    -0.08
    POSITIVE LOGITS
     Drive
    0.13
     People
    0.12
    Drive
    0.12
     You
    0.12
     Gmail
    0.12
    People
    0.12
     Directory
    0.11
     Classroom
    0.11
     Sheets
    0.11
    Sheets
    0.11
    Activations Density 0.007%

    No Known Activations