© 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. 18706
    Prev
    Next
    INDEX
    Explanations

    say "C" words

    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
     '/../
    -0.08
     prepend
    -0.08
    IMATION
    -0.08
     divide
    -0.08
     split
    -0.08
     halve
    -0.07
    nete
    -0.07
     downgrade
    -0.07
     divides
    -0.07
     estimate
    -0.07
    POSITIVE LOGITS
     completing
    0.11
     Completing
    0.11
    第四
    0.11
     fourth
    0.11
     cuarta
    0.10
     consequently
    0.10
     Fourth
    0.10
     culminating
    0.10
    四
    0.10
     quatrième
    0.10
    Activations Density 0.008%

    No Known Activations