© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 52278
    Prev
    Next
    INDEX
    Explanations

    kem

    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
    Negative Logits
     vini
    -0.08
    型号
    -0.08
    IPP
    -0.08
    入
    -0.08
     vasos
    -0.07
     seri
    -0.07
     xxx
    -0.07
    ودی
    -0.07
    号码
    -0.07
     paso
    -0.07
    POSITIVE LOGITS
    support
    0.08
     кар
    0.08
     supporter
    0.08
    istance
    0.08
     teal
    0.08
     payoff
    0.08
    gear
    0.07
     cheerful
    0.07
    _TE
    0.07
    pt
    0.07
    Activations Density 0.000%

    No Known Activations