© 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. 78257
    Prev
    Next
    INDEX
    Explanations

    mathematical optimization 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
     opcode
    -0.09
    Opcode
    -0.09
    opcode
    -0.09
     vet
    -0.08
     nif
    -0.08
     Sgt
    -0.08
    NUM
    -0.08
    _OPCODE
    -0.08
     Parliament
    -0.08
     футбол
    -0.08
    POSITIVE LOGITS
    .minimum
    0.10
     Ratio
    0.10
    Ratio
    0.09
     ratio
    0.09
    _ratio
    0.09
     nozzle
    0.09
    ^{-
    0.09
    ratio
    0.09
     dominates
    0.09
     ratios
    0.09
    Activations Density 0.080%

    No Known Activations