© 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. 19-RESID-POST-AA
    11. 19059
    Prev
    Next
    INDEX
    Explanations

    at

    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
    ('.
    -0.09
     использование
    -0.08
    없
    -0.08
    Dust
    -0.08
     использовать
    -0.08
    ('#
    -0.08
    wendung
    -0.08
    -specific
    -0.08
    การ
    -0.08
    /C
    -0.07
    POSITIVE LOGITS
     tốc
    0.13
     υψη
    0.13
     constant
    0.11
     vysok
    0.11
     yüksək
    0.11
     speeds
    0.11
     velocidades
    0.10
     assumed
    0.10
     konstant
    0.10
     velocidade
    0.10
    Activations Density 0.021%

    No Known Activations