© 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. 21799
    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
    ness
    -0.12
    થી
    -0.11
    ellaneous
    -0.10
    นำ
    -0.09
    ે
    -0.09
    اً
    -0.09
    น้ำ
    -0.09
    n't
    -0.09
    ration
    -0.09
    entication
    -0.09
    POSITIVE LOGITS
    ğ
    0.15
    ğu
    0.14
    fta
    0.13
    ज़
    0.12
    ctors
    0.12
    ftar
    0.12
    ško
    0.12
    ऊन
    0.12
    zzel
    0.12
    šlo
    0.12
    Activations Density 0.040%

    No Known Activations