© 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. 50229
    Prev
    Next
    INDEX
    Explanations

    breaking down/unpacking

    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
     предусматри
    -0.09
    amples
    -0.08
     предусмотр
    -0.08
    _samples
    -0.08
     atụmatụ
    -0.08
    preset
    -0.08
     prominently
    -0.08
    Sample
    -0.08
    _sample
    -0.08
    autions
    -0.08
    POSITIVE LOGITS
    逐
    0.17
     unpack
    0.16
     unravel
    0.15
    拆
    0.15
     dissect
    0.14
    来看
    0.14
     Breakdown
    0.12
     разобраться
    0.12
     Breaking
    0.12
     breakdown
    0.12
    Activations Density 0.047%

    No Known Activations