© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 94847
    Prev
    Next
    INDEX
    Explanations

    R

    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
     militia
    -0.08
    ائی
    -0.08
    Updates
    -0.08
     cab
    -0.08
    Models
    -0.07
    势
    -0.07
     сег
    -0.07
    Gr
    -0.07
     оч
    -0.07
     preach
    -0.07
    POSITIVE LOGITS
     ISO
    0.08
     lid
    0.07
     breathable
    0.07
     capacities
    0.07
    ભાગ
    0.07
     soles
    0.07
     atmos
    0.07
     jars
    0.07
     ભાવ
    0.07
     SPI
    0.07
    Activations Density 0.002%

    No Known Activations