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. 76116
    Prev
    Next
    INDEX
    Explanations

    there

    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
     fich
    -0.08
     दे
    -0.08
     klappt
    -0.07
     eucalyptus
    -0.07
     But
    -0.07
     Inuit
    -0.07
     trays
    -0.07
     deficient
    -0.07
     bekam
    -0.07
     deler
    -0.07
    POSITIVE LOGITS
    关联
    0.08
    这个
    0.08
    Adaptor
    0.08
    联系
    0.08
    Tie
    0.08
    OVA
    0.08
    的数据
    0.08
    িয়
    0.08
    cript
    0.08
    	bg
    0.08
    Activations Density 0.000%

    No Known Activations