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. 65283
    Prev
    Next
    INDEX
    Explanations

    function transformations

    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
    Divider
    -0.09
     topped
    -0.08
     audiobook
    -0.08
    LLLL
    -0.08
     fillers
    -0.08
     peat
    -0.08
    OCK
    -0.08
     ministry
    -0.08
     episódios
    -0.08
     Afghanistan
    -0.07
    POSITIVE LOGITS
     transformation
    0.10
     transformations
    0.09
     mapping
    0.08
     Latitude
    0.08
    latitude
    0.08
     latency
    0.08
     Renaissance
    0.08
     velocity
    0.08
     Coordinates
    0.08
     axes
    0.08
    Activations Density 0.015%

    No Known Activations