© 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. 20617
    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
    different
    -0.07
    workflow
    -0.07
    CGRect
    -0.07
     gioco
    -0.07
    kay
    -0.07
    GE
    -0.07
    elb
    -0.07
    game
    -0.07
    AS
    -0.07
     Workflow
    -0.07
    POSITIVE LOGITS
     multiplied
    0.17
     ×
    0.16
     Multiply
    0.16
     multiply
    0.15
    Multiply
    0.15
     multiplying
    0.15
    ×
    0.14
    乘
    0.14
    *num
    0.13
     multiplication
    0.13
    Activations Density 0.044%

    No Known Activations