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. 120235
    Prev
    Next
    INDEX
    Explanations

    /bin

    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
     Zu
    -0.09
    Faces
    -0.08
    Zu
    -0.08
    244
    -0.08
    _scheme
    -0.07
    課
    -0.07
     Kar
    -0.07
     पास
    -0.07
     Nx
    -0.07
     Pitt
    -0.07
    POSITIVE LOGITS
    :aload
    0.09
     oval
    0.07
     Maver
    0.07
    :not
    0.07
     Bart
    0.07
    imap
    0.07
     Bernard
    0.07
     остав
    0.07
     tá
    0.07
    ';↵↵/
    0.07
    Activations Density 0.001%

    No Known Activations