© 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. 23-RESID-POST-AA
    11. 49294
    Prev
    Next
    INDEX
    Explanations

    EX

    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
     Northern
    -0.08
    .you
    -0.08
    bury
    -0.07
    -ex
    -0.07
     schlagen
    -0.07
     tycker
    -0.07
    .user
    -0.07
    _states
    -0.07
     Burke
    -0.07
     BODY
    -0.07
    POSITIVE LOGITS
    Gi
    0.10
     Gi
    0.09
    UIS
    0.08
    ജി
    0.07
    ODS
    0.07
     resent
    0.07
    rios
    0.07
    �
    0.07
    ifad
    0.07
    'emp
    0.07
    Activations Density 0.000%

    No Known Activations