© 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. 21803
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    itare
    -0.11
     trois
    -0.09
     quatre
    -0.09
    five
    -0.09
    ಗ್ರ
    -0.09
    traj
    -0.09
    three
    -0.09
     (*(
    -0.08
     cinq
    -0.08
     (--
    -0.08
    POSITIVE LOGITS
     early
    0.14
     frühen
    0.12
     início
    0.11
     earlier
    0.10
     primeiros
    0.10
     раньше
    0.09
    early
    0.09
     الاول
    0.09
    Early
    0.09
    早
    0.09
    Activations Density 0.006%

    No Known Activations