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. 27534
    Prev
    Next
    INDEX
    Explanations

    half

    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
     steel
    -0.08
     tal
    -0.07
     artifacts
    -0.07
     resignation
    -0.07
    zet
    -0.07
     metal
    -0.07
    -0.07
    deprecated
    -0.07
    لع
    -0.07
     notation
    -0.07
    POSITIVE LOGITS
     randomly
    0.11
     tilfeldig
    0.11
     statistically
    0.10
     Random
    0.10
     Approximately
    0.10
     بنسبة
    0.09
     evenly
    0.09
     Mir
    0.09
    /random
    0.09
     tilfeld
    0.09
    Activations Density 0.027%

    No Known Activations