© 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. 20514
    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
     HR
    -0.08
     Hz
    -0.07
     Alive
    -0.07
     має
    -0.07
     Down
    -0.07
     vitr
    -0.07
     ổ
    -0.07
    "is
    -0.07
     High
    -0.07
     am
    -0.07
    POSITIVE LOGITS
    նշ
    0.10
    <|message|>
    0.10
    ‑
    0.10
     ჩვენს
    0.10
    -hasp
    0.09
    -​
    0.09
     ჩვენი
    0.09
     අප
    0.09
     аҧс
    0.09
    արաբ
    0.09
    Activations Density 0.008%

    No Known Activations