© 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 EvalsExportsAPI 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. 21055
    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
     specifically
    -0.09
     with
    -0.08
     previs
    -0.08
     específico
    -0.08
     enger
    -0.08
     spes
    -0.07
     خاص
    -0.07
    خاص
    -0.07
     specif
    -0.07
     dengan
    -0.07
    POSITIVE LOGITS
    ებისა
    0.14
     ასევე
    0.14
    ികളും
    0.13
     și
    0.13
     మరియు
    0.13
    ിയും
    0.13
     पनि
    0.13
    ാനും
    0.13
     նաև
    0.12
     եւ
    0.12
    Activations Density 0.016%

    No Known Activations