© 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 EvalsExportsAPI 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. 20580
    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
    *:
    -0.08
    :
    -0.08
     davvero
    -0.07
     "";
    -0.07
     Niemand
    -0.07
    Proper
    -0.07
    -padding
    -0.07
     outcome
    -0.07
    Pending
    -0.07
     AND
    -0.07
    POSITIVE LOGITS
     relations
    0.10
     ratios
    0.10
     angles
    0.09
    relations
    0.09
     directeur
    0.09
    отнош
    0.09
     relation
    0.09
     ചര
    0.09
    ratio
    0.09
     ratio
    0.09
    Activations Density 0.019%

    No Known Activations