© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 19367
    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
    -equipped
    -0.10
    -oriented
    -0.10
     tavalla
    -0.09
    ('../../../
    -0.09
     nél
    -0.09
     dışında
    -0.09
    Initialized
    -0.09
     Jahrze
    -0.09
    ('../../
    -0.09
    ('/')
    -0.08
    POSITIVE LOGITS
    soil
    0.11
    zone
    0.10
    layer
    0.09
    formation
    0.09
    section
    0.09
    move
    0.09
    urn
    0.09
    scene
    0.09
    midd
    0.09
    riff
    0.09
    Activations Density 0.003%

    No Known Activations