© 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. 79034
    Prev
    Next
    INDEX
    Explanations

    preceding

    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
     reproduc
    -0.09
     reproduction
    -0.08
    طلق
    -0.08
     reprodu
    -0.07
     ceremonia
    -0.07
     bénéfici
    -0.07
     contestants
    -0.07
    Virus
    -0.07
    -0.07
    ್ಡ್
    -0.07
    POSITIVE LOGITS
    黄色
    0.09
     preceding
    0.09
    preced
    0.09
     “…
    0.09
    “…
    0.09
    勢
    0.08
     imediatamente
    0.08
     precedente
    0.08
     inmediatamente
    0.08
     polis
    0.08
    Activations Density 0.008%
    No Known Activations