© 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. 11-RESID-POST-AA
    11. 71385
    Prev
    Next
    INDEX
    Explanations

    remainders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    альних
    -0.08
     Lone
    -0.08
     beheren
    -0.08
    \Models
    -0.08
    บริการ
    -0.08
    _management
    -0.08
     impatient
    -0.08
     témo
    -0.08
    Puzzle
    -0.08
    .Malformed
    -0.07
    POSITIVE LOGITS
     divisible
    0.11
     новая
    0.09
     Vet
    0.09
    :new
    0.08
     divis
    0.08
     নতুন
    0.08
     avenida
    0.08
    oeid
    0.08
    ودي
    0.08
    98
    0.07
    Activations Density 0.050%

    No Known Activations