© 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. 78836
    Prev
    Next
    INDEX
    Explanations

    reciprocal

    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
     anten
    -0.09
     Afro
    -0.08
     бы
    -0.08
    _gui
    -0.08
     cô
    -0.08
     aqu
    -0.08
    แต่
    -0.08
    tips
    -0.07
     minder
    -0.07
     Gn
    -0.07
    POSITIVE LOGITS
    -thirds
    0.09
    是多少
    0.08
     множ
    0.08
    -lived
    0.08
    (eval
    0.08
    美元
    0.07
     Numer
    0.07
     Larry
    0.07
     edilen
    0.07
    -Life
    0.07
    Activations Density 0.004%

    No Known Activations