© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91543
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
    _BOOL
    -0.09
     embrace
    -0.08
     survivor
    -0.08
     đa
    -0.07
     cooperation
    -0.07
    Bool
    -0.07
     evening
    -0.07
     تبد
    -0.07
     entert
    -0.07
     uninterrupted
    -0.07
    POSITIVE LOGITS
     centroid
    0.10
     radius
    0.10
     centers
    0.10
     planes
    0.09
     метро
    0.09
     विमान
    0.09
     dilation
    0.09
    Plane
    0.09
    radius
    0.09
     plane
    0.09
    Activations Density 0.065%

    No Known Activations