© 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. 51603
    Prev
    Next
    INDEX
    Explanations

    侧

    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
    סה
    -0.09
    sans
    -0.09
    sn
    -0.09
    sid
    -0.08
    קום
    -0.08
    atory
    -0.08
    েটে
    -0.08
    sun
    -0.08
    atoire
    -0.08
    צ
    -0.08
    POSITIVE LOGITS
    重
    0.17
     重
    0.13
    重新
    0.11
    重点
    0.11
    重大
    0.10
    重量
    0.10
     إعادة
    0.10
    _Re
    0.09
     rewriting
    0.09
    re
    0.09
    Activations Density 0.001%

    No Known Activations