© 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. 51031
    Prev
    Next
    INDEX
    Explanations

    treat

    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
    weak
    -0.09
    Older
    -0.09
    Weak
    -0.08
    ED
    -0.08
     Weak
    -0.08
     gick
    -0.08
    Education
    -0.08
    免费观看
    -0.08
    авед
    -0.08
    .vm
    -0.08
    POSITIVE LOGITS
    ise
    0.22
    ises
    0.20
    ISE
    0.14
    yse
    0.13
    izes
    0.12
    ising
    0.12
    ised
    0.11
    iser
    0.11
    ize
    0.11
    isest
    0.10
    Activations Density 0.007%

    No Known Activations