© 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. 21384
    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
     એટલે
    -0.11
     ნიშნავს
    -0.10
     are
    -0.10
     thus
    -0.10
     can
    -0.09
     actually
    -0.09
     საუკეთ
    -0.09
     ანუ
    -0.09
     ყველაფ
    -0.09
     écht
    -0.09
    POSITIVE LOGITS
    both
    0.10
     både
    0.10
     दोनों
    0.10
    Both
    0.09
    NIEnv
    0.09
     Both
    0.09
    grö
    0.09
     دونوں
    0.09
     sowohl
    0.09
     both
    0.08
    Activations Density 0.030%

    No Known Activations