© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 69665
    Prev
    Next
    INDEX
    Explanations

    get

    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
     나타
    -0.08
     hectare
    -0.08
     complexes
    -0.07
    음을
    -0.07
    hei
    -0.07
     unica
    -0.07
     अत
    -0.07
     motorista
    -0.07
     ondanks
    -0.07
     vermeld
    -0.07
    POSITIVE LOGITS
    inspect
    0.09
     inspect
    0.08
    ама
    0.08
     оценки
    0.08
     کیفیت
    0.08
     Lens
    0.08
     Owen
    0.08
     کمک
    0.08
     UD
    0.07
     Inspection
    0.07
    Activations Density 0.001%

    No Known Activations