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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 65176
    Prev
    Next
    INDEX
    Explanations

    finite

    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
     Seam
    -0.08
     Oma
    -0.08
    �
    -0.08
     realizada
    -0.08
    	stream
    -0.08
     Cam
    -0.08
     Chrysler
    -0.07
     whitening
    -0.07
     publicada
    -0.07
     Вып
    -0.07
    POSITIVE LOGITS
    ன
    0.08
     veremos
    0.08
    =np
    0.08
     موجود
    0.07
    ocytes
    0.07
     forests
    0.07
     tempt
    0.07
    uristic
    0.07
     пространства
    0.07
    ournaments
    0.07
    Activations Density 0.003%

    No Known Activations