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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 45724
    Prev
    Next
    INDEX
    Explanations

    success

    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
     unfamiliar
    -0.09
     общения
    -0.08
    	m
    -0.08
     iced
    -0.08
     acquaintances
    -0.08
     conveys
    -0.08
    になります
    -0.07
     परेश
    -0.07
     сиг
    -0.07
     conveying
    -0.07
    POSITIVE LOGITS
    成果
    0.12
     successes
    0.12
     efficacy
    0.11
     SUCCESS
    0.11
     effectiveness
    0.11
     Successfully
    0.11
    ，截至
    0.11
     NGOs
    0.10
     neoliberal
    0.10
     achieved
    0.10
    Activations Density 0.050%

    No Known Activations