© 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. 50843
    Prev
    Next
    INDEX
    Explanations

    .

    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
     killexams
    -0.09
     definição
    -0.08
     certifications
    -0.08
     définition
    -0.08
     comparisons
    -0.08
     əldə
    -0.08
     anual
    -0.08
    认证
    -0.08
     айыр
    -0.08
     definición
    -0.08
    POSITIVE LOGITS
     continuation
    0.38
     continuing
    0.35
     continuar
    0.35
    Continuation
    0.34
     continue
    0.34
    继续
    0.33
    Continue
    0.33
     Continue
    0.33
     continuer
    0.32
     pokrač
    0.32
    Activations Density 0.103%

    No Known Activations