© 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. 63663
    Prev
    Next
    INDEX
    Explanations

    translation, math, analysis

    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
     IN
    -0.08
     esim
    -0.08
     (
    -0.07
     IM
    -0.07
     IH
    -0.07
     uut
    -0.07
     RT
    -0.07
    ,
    -0.07
     miks
    -0.07
     sister
    -0.07
    POSITIVE LOGITS
     действительно
    0.09
     대신
    0.09
     באמת
    0.09
     مذ
    0.09
     보
    0.09
    มน
    0.08
     مزید
    0.08
    จริง
    0.08
     Indeed
    0.08
     naprawdę
    0.08
    Activations Density 0.255%

    No Known Activations