© 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. 23-RESID-POST-AA
    11. 50208
    Prev
    Next
    INDEX
    Explanations

    .

    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
    per
    -0.10
    char
    -0.10
    database
    -0.10
    _Per
    -0.09
    perk
    -0.09
    national
    -0.09
    _per
    -0.09
    name
    -0.09
    errors
    -0.09
    degree
    -0.09
    POSITIVE LOGITS
     dink
    0.08
     kval
    0.08
     mo
    0.07
     lọ
    0.07
    ILT
    0.07
    0.07
     transformers
    0.07
     zh
    0.07
     thrust
    0.07
     potem
    0.07
    Activations Density 0.776%

    No Known Activations