© 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. 50897
    Prev
    Next
    INDEX
    Explanations

    say "2"

    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
     เทคนิค
    -0.09
     Giuseppe
    -0.09
     técnica
    -0.09
     النباتات
    -0.09
     tecnica
    -0.09
    .Linear
    -0.08
    国语
    -0.08
    CREASE
    -0.08
     кни
    -0.08
    روعات
    -0.08
    POSITIVE LOGITS
     SOC
    0.15
     Saa
    0.13
    SOC
    0.12
    270
    0.12
     audits
    0.12
     compliant
    0.11
     compliance
    0.11
     талап
    0.11
    -com
    0.11
     인증
    0.11
    Activations Density 0.011%

    No Known Activations