© 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. 79091
    Prev
    Next
    INDEX
    Explanations

    white

    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
     ingr
    -0.10
    Outputs
    -0.08
     riport
    -0.08
    Discrete
    -0.08
     वास्तविक
    -0.07
     Eats
    -0.07
    Inser
    -0.07
     discrete
    -0.07
     entrances
    -0.07
     barras
    -0.07
    POSITIVE LOGITS
     Sauvignon
    0.09
     Whites
    0.08
     putih
    0.08
    .iso
    0.08
    .nio
    0.08
     frisse
    0.08
     whites
    0.08
     Ries
    0.08
     Payne
    0.07
     kaj
    0.07
    Activations Density 0.004%

    No Known Activations