© 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. 21575
    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
    _request
    -0.09
    _mul
    -0.08
    оят
    -0.08
    _purchase
    -0.08
     kaikki
    -0.08
    _check
    -0.08
    _unique
    -0.07
    _len
    -0.07
    _focus
    -0.07
     احتمال
    -0.07
    POSITIVE LOGITS
     vergeet
    0.08
    chemist
    0.07
     others
    0.07
     innych
    0.07
    ’après
    0.07
     complied
    0.07
    ిస్
    0.07
     drugih
    0.07
     those
    0.07
    isant
    0.07
    Activations Density 0.913%

    No Known Activations