© 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. 22692
    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
     later
    -0.09
    later
    -0.08
     thereafter
    -0.08
    后来
    -0.08
     wanting
    -0.08
    eliers
    -0.08
     quienes
    -0.07
     posteriormente
    -0.07
    -ж
    -0.07
     ones
    -0.07
    POSITIVE LOGITS
     another
    0.12
    another
    0.12
    Another
    0.11
     Another
    0.11
     otra
    0.11
    Outra
    0.11
    Otra
    0.11
     Outra
    0.11
     మరో
    0.10
    Otro
    0.10
    Activations Density 0.001%

    No Known Activations