© 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. 20468
    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
    <|reserved_200009|>
    -0.09
    ուզ
    -0.09
    ுப
    -0.09
     durchaus
    -0.09
     tagħha
    -0.09
    ующее
    -0.09
    ‍ഗ്രസ്
    -0.09
    ունակ
    -0.09
    τικότητα
    -0.09
     især
    -0.09
    POSITIVE LOGITS
    angles
    0.12
    ilateral
    0.10
    angular
    0.09
    on
    0.09
    /
    0.09
    _angles
    0.09
     θ
    0.08
    (vertices
    0.08
    _a
    0.08
    (CG
    0.08
    Activations Density 0.004%

    No Known Activations