© 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 EvalsExportsinterp-engineNEWAPI 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. 111467
    Prev
    Next
    INDEX
    Explanations

    period

    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
     त्या
    -0.09
     Drew
    -0.08
    Determ
    -0.08
     aquelas
    -0.08
     ákve
    -0.08
    Infrastructure
    -0.08
    ામ
    -0.07
    _INTEGER
    -0.07
     calculates
    -0.07
     bestimmen
    -0.07
    POSITIVE LOGITS
     teens
    0.09
     quir
    0.09
     sara
    0.09
    rais
    0.08
     septembre
    0.08
     Pocket
    0.08
    olda
    0.08
     WIFI
    0.08
     начина
    0.08
     Weird
    0.08
    Activations Density 0.001%

    No Known Activations