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. 119171
    Prev
    Next
    INDEX
    Explanations

    Readable text formatting

    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
    .In
    -0.08
    .z
    -0.08
    .Rem
    -0.07
    .qu
    -0.07
     minor
    -0.07
     Kunde
    -0.07
     trajectories
    -0.07
     permutation
    -0.07
    )
    -0.07
     telemetry
    -0.07
    POSITIVE LOGITS
     readability
    0.11
     chunks
    0.10
     chunky
    0.10
    chunks
    0.09
    Chunk
    0.09
     aantrekkelijke
    0.09
     Chunk
    0.09
    chunk
    0.09
     Canva
    0.09
     serif
    0.09
    Activations Density 0.022%

    No Known Activations