Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 78419
    Prev
    Next
    INDEX
    Explanations

    waves

    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
     intervención
    -0.08
     devote
    -0.08
     Übers
    -0.08
     രക്ഷ
    -0.08
    变态
    -0.08
    ένα
    -0.08
     intervent
    -0.08
    	msg
    -0.07
     evangel
    -0.07
     مؤسسة
    -0.07
    POSITIVE LOGITS
     alami
    0.09
     sitcom
    0.08
     priro
    0.08
    自然
    0.08
     polished
    0.08
     naturelle
    0.08
     naturale
    0.08
     naturel
    0.08
     naturelles
    0.08
     natur
    0.08
    Activations Density 0.006%

    No Known Activations