© 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. 19634
    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
    iraan
    -0.08
    vano
    -0.08
     období
    -0.08
    免费观看
    -0.08
    обод
    -0.08
     nodded
    -0.07
    уков
    -0.07
    ’anno
    -0.07
    ‍വ
    -0.07
    ’avait
    -0.07
    POSITIVE LOGITS
     stringent
    0.37
     stric
    0.37
     restrictive
    0.29
     stronger
    0.28
     strict
    0.28
     কঠ
    0.25
    严格
    0.25
     tighter
    0.25
     कठ
    0.24
     строг
    0.24
    Activations Density 0.053%

    No Known Activations