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. 113039
    Prev
    Next
    INDEX
    Explanations

    geometric transformations

    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
     stall
    -0.08
     dobro
    -0.08
     PA
    -0.08
     largest
    -0.08
     ત્યારે
    -0.07
     самого
    -0.07
     biggest
    -0.07
    _neg
    -0.07
     banning
    -0.07
    [ch
    -0.07
    POSITIVE LOGITS
     kapcsolat
    0.09
    akur
    0.09
    교육
    0.07
     Andal
    0.07
     henne
    0.07
    +"/
    0.07
     Krishna
    0.07
    ינם
    0.07
    ensitive
    0.07
     Compared
    0.07
    Activations Density 0.000%

    No Known Activations