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. 58979
    Prev
    Next
    INDEX
    Explanations

    Hertzsprung-Russell diagrams

    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
     celebration
    -0.08
     ta
    -0.08
    IRON
    -0.08
    -file
    -0.07
    -f
    -0.07
     limited
    -0.07
    Limited
    -0.07
    .did
    -0.07
    PR
    -0.07
     Brendan
    -0.07
    POSITIVE LOGITS
     grotere
    0.09
     critérios
    0.08
     pasajeros
    0.08
     '-',
    0.08
     coches
    0.08
    aliya
    0.08
     critères
    0.08
    üss
    0.08
    alag
    0.08
     "))↵
    0.08
    Activations Density 0.000%

    No Known Activations