© 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. 23-RESID-POST-AA
    11. 47670
    Prev
    Next
    INDEX
    Explanations

    atomic weights and nutrition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     행
    -0.08
    words
    -0.08
     Maxamed
    -0.08
    .words
    -0.08
     Assertion
    -0.08
     SUB
    -0.08
     ints
    -0.08
     Sub
    -0.07
    Sub
    -0.07
    ിന്റ
    -0.07
    POSITIVE LOGITS
     respiratory
    0.09
     controllers
    0.08
    Controllers
    0.08
     merkez
    0.08
     güzel
    0.08
     colocando
    0.08
     kaw
    0.08
     inject
    0.08
     pul
    0.07
     vivid
    0.07
    Activations Density 0.001%

    No Known Activations