© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29668
    Prev
    Next
    INDEX
    Explanations

    :

    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
     neatly
    -0.09
    后的
    -0.08
     sil
    -0.08
    均
    -0.07
    ിള
    -0.07
    ുള്ള
    -0.07
    完整
    -0.07
    ilk
    -0.07
    四
    -0.07
     dettagli
    -0.07
    POSITIVE LOGITS
     atualmente
    0.09
     Actualmente
    0.09
     Historically
    0.08
     actualmente
    0.08
     Examination
    0.08
     Messiah
    0.08
     Hmm
    0.08
     prowad
    0.08
     /*↵
    0.08
     Examine
    0.08
    Activations Density 0.027%

    No Known Activations