© 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. 23-RESID-POST-AA
    11. 47704
    Prev
    Next
    INDEX
    Explanations

    groups

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unattended
    -0.09
     duwan
    -0.09
     drained
    -0.08
     journalist
    -0.08
    מך
    -0.08
    unud
    -0.08
    Mandatory
    -0.08
    מית
    -0.08
     defens
    -0.08
     mandatory
    -0.08
    POSITIVE LOGITS
     group
    0.19
     subgroup
    0.18
     actions
    0.18
     permutations
    0.18
     Actions
    0.17
    _actions
    0.16
     acting
    0.16
     transformations
    0.16
     PSL
    0.16
    Actions
    0.16
    Activations Density 0.021%

    No Known Activations