© 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. 18911
    Prev
    Next
    INDEX
    Explanations

    say "."

    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
     مفهوم
    -0.09
     اسے
    -0.08
    免费资料
    -0.08
     مرکز
    -0.08
     zuiden
    -0.08
     différente
    -0.08
     мең
    -0.08
     سولې
    -0.08
     دوستان
    -0.08
    ியான
    -0.08
    POSITIVE LOGITS
    _DT
    0.09
    _SUM
    0.08
    DT
    0.08
    sum
    0.08
    ̂
    0.08
    _sum
    0.08
     എന്ന
    0.07
     where
    0.07
    SUMMARY
    0.07
    Sum
    0.07
    Activations Density 0.004%

    No Known Activations