Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 1902
    Prev
    Next
    INDEX
    Explanations

    vegetables, especially squash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bond
    -0.08
     glamorous
    -0.08
     musique
    -0.08
     tuvo
    -0.08
     primitives
    -0.08
    ahami
    -0.08
     jih
    -0.08
     audiobook
    -0.08
     infra
    -0.08
     desse
    -0.08
    POSITIVE LOGITS
     lett
    0.09
     Kiev
    0.08
     Kyiv
    0.08
    Crop
    0.08
     beet
    0.08
    .An
    0.08
     Kale
    0.08
    Zip
    0.08
     underst
    0.07
    ांश
    0.07
    Activations Density 0.083%

    No Known Activations