© 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. 19-RESID-POST-AA
    11. 103449
    Prev
    Next
    INDEX
    Explanations

    Agreements

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     அனைத்து
    -0.10
    Every
    -0.10
     all
    -0.10
    _all
    -0.09
    every
    -0.09
     모두
    -0.09
     every
    -0.09
    All
    -0.09
     ಎಲ್ಲಾ
    -0.09
    all
    -0.09
    POSITIVE LOGITS
    个百分点
    0.09
    одержание
    0.09
     onderwerpen
    0.09
     Mind
    0.08
     voelen
    0.08
     onderwerp
    0.08
    Mind
    0.08
     minuten
    0.08
     ibintu
    0.08
     zvinhu
    0.08
    Activations Density 0.000%

    No Known Activations