© 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. 44757
    Prev
    Next
    INDEX
    Explanations

    integrals

    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
     എ
    -0.08
    .connections
    -0.07
     Trojan
    -0.07
     Tal
    -0.07
     Winn
    -0.07
     talentos
    -0.07
     ek
    -0.07
     ciclos
    -0.07
     нар
    -0.07
     Veterans
    -0.07
    POSITIVE LOGITS
     shoreline
    0.09
     coastline
    0.09
    :number
    0.08
     kawasan
    0.08
     flown
    0.08
     fu
    0.08
    subtotal
    0.08
     شمال
    0.08
     Antalya
    0.08
     얼마
    0.08
    Activations Density 0.007%

    No Known Activations