© 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. 45328
    Prev
    Next
    INDEX
    Explanations

    Override

    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
    ernal
    -0.08
    ユ
    -0.08
    .pl
    -0.07
    ांग
    -0.07
    。一
    -0.07
     vracht
    -0.07
     marge
    -0.07
    ør
    -0.07
    afi
    -0.07
    。
    -0.07
    POSITIVE LOGITS
     рекоменду
    0.09
     verhindert
    0.08
    ваем
    0.08
    proble
    0.08
     BEN
    0.08
     BEST
    0.08
    κου
    0.08
     borrower
    0.08
    _CHANGED
    0.07
     _(
    0.07
    Activations Density 0.001%

    No Known Activations