© 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. 94669
    Prev
    Next
    INDEX
    Explanations

    AI instructions

    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
     cousins
    -0.09
     zařízení
    -0.08
     இர
    -0.08
    ách
    -0.08
     Penguins
    -0.08
     Cous
    -0.08
     capacitor
    -0.08
     Leute
    -0.07
     ironically
    -0.07
     exclude
    -0.07
    POSITIVE LOGITS
     nutrientes
    0.08
     ratings
    0.08
    িকে
    0.08
    िला
    0.08
    hman
    0.08
     classifications
    0.07
    Classification
    0.07
     parameters
    0.07
    (constants
    0.07
    ेख
    0.07
    Activations Density 0.002%

    No Known Activations