© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51307
    Prev
    Next
    INDEX
    Explanations

    optical signal processing

    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
     Đi
    -0.08
     процесса
    -0.08
    \Input
    -0.08
     Brands
    -0.08
     Gew
    -0.07
    ürt
    -0.07
    .patch
    -0.07
     wej
    -0.07
     Jazz
    -0.07
    process
    -0.07
    POSITIVE LOGITS
    -select
    0.15
    -dependent
    0.15
    -sensitive
    0.14
    dependent
    0.12
    Sensitive
    0.12
    _select
    0.12
     dependent
    0.12
    select
    0.11
     sensitive
    0.11
     estimation
    0.11
    Activations Density 0.012%

    No Known Activations