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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 30262
    Prev
    Next
    INDEX
    Explanations

    kid friendly

    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
     pequeño
    -0.08
     abr
    -0.08
     beads
    -0.07
     rosa
    -0.07
     pequeno
    -0.07
     bead
    -0.07
     corto
    -0.07
     Instruments
    -0.07
    enic
    -0.07
    otel
    -0.07
    POSITIVE LOGITS
    ′s
    0.09
     அனைவர
    0.09
     eased
    0.09
     ids
    0.08
     easing
    0.08
     agreeable
    0.08
    ively
    0.08
     piac
    0.08
     /^[
    0.08
    ={()
    0.08
    Activations Density 0.005%

    No Known Activations