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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 22554
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     centrale
    -0.09
     according
    -0.09
     According
    -0.08
     विशेष
    -0.08
     together
    -0.08
     먼저
    -0.08
     without
    -0.08
     pertenc
    -0.08
    .authenticate
    -0.08
     {}'.
    -0.08
    POSITIVE LOGITS
    mt
    0.14
    margin
    0.13
     margin
    0.11
     mt
    0.11
    Divider
    0.11
    divider
    0.11
    hr
    0.11
    _margin
    0.11
    	margin
    0.11
    -divider
    0.11
    Activations Density 0.002%

    No Known Activations