© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 71516
    Prev
    Next
    INDEX
    Explanations

    Uses separators like commas

    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
    -0.07
     working
    -0.07
    -0.06
    -0.06
     paras
    -0.06
                            
    -0.06
     inter
    -0.06
    .Side
    -0.06
    Data
    -0.06
    -0.06
    POSITIVE LOGITS
     asli
    0.10
     gelief
    0.09
     auta
    0.09
     métiers
    0.09
     Februar
    0.09
     février
    0.09
    んな
    0.08
     dared
    0.08
     febrero
    0.08
     росс
    0.08
    Activations Density 0.212%
    No Known Activations