© 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. 11-RESID-POST-AA
    11. 69606
    Prev
    Next
    INDEX
    Explanations

    icon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .No
    -0.09
     موارد
    -0.08
    feel
    -0.08
    .Message
    -0.08
    .Yes
    -0.08
    .Footer
    -0.08
    email
    -0.08
     �
    -0.08
    Stan
    -0.07
    .Email
    -0.07
    POSITIVE LOGITS
     tuo
    0.09
     philosophers
    0.08
     tua
    0.08
    gios
    0.08
     grotes
    0.08
     gird
    0.08
     Gelen
    0.08
    чим
    0.08
     yin
    0.08
     bäst
    0.08
    Activations Density 0.008%

    No Known Activations