© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 47578
    Prev
    Next
    INDEX
    Explanations

    double

    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
    izing
    -0.13
    Providing
    -0.12
    Writing
    -0.12
    izacja
    -0.12
    ISING
    -0.12
    icating
    -0.11
    Offering
    -0.11
     Providing
    -0.11
     Offering
    -0.11
    tributing
    -0.11
    POSITIVE LOGITS
    -check
    0.20
     പരിശോധ
    0.14
    check
    0.13
     check
    0.13
    _check
    0.12
     again
    0.12
    -confirm
    0.12
    .check
    0.12
    count
    0.12
     the
    0.12
    Activations Density 0.012%

    No Known Activations