© 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. 11-RESID-POST-AA
    11. 64095
    Prev
    Next
    INDEX
    Explanations

    code with math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Accountability
    -0.08
    Tenant
    -0.08
     franchises
    -0.08
    äv
    -0.08
     accountable
    -0.08
    Agence
    -0.08
     centralized
    -0.08
     Ticket
    -0.07
     accountability
    -0.07
     attribution
    -0.07
    POSITIVE LOGITS
    .linspace
    0.14
    .arange
    0.11
    =np
    0.10
     plotting
    0.10
     לאורך
    0.10
    [np
    0.09
     plt
    0.09
     массив
    0.09
     arrays
    0.09
    _interp
    0.09
    Activations Density 0.009%

    No Known Activations