© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95823
    Prev
    Next
    INDEX
    Explanations

    aky

    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
    engd
    -0.08
    推
    -0.08
     recalled
    -0.08
     diễn
    -0.08
     massif
    -0.07
    _stdout
    -0.07
    ’inter
    -0.07
    stdout
    -0.07
    登
    -0.07
    936
    -0.07
    POSITIVE LOGITS
     irgendwie
    0.08
     zufrieden
    0.08
     subtle
    0.08
     dissatisfied
    0.08
     dissatisfaction
    0.08
    Readonly
    0.08
     epoxy
    0.08
     slags
    0.08
     смер
    0.08
     dishon
    0.08
    Activations Density 0.001%

    No Known Activations