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. 11-RESID-POST-AA
    6. 29966
    Prev
    Next
    INDEX
    Explanations

    down

    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
     terminado
    -0.08
    Scripts
    -0.08
    /=
    -0.08
     Scripts
    -0.07
     scripts
    -0.07
    terminated
    -0.07
     disfr
    -0.07
     jeste
    -0.07
     Ler
    -0.07
     khale
    -0.07
    POSITIVE LOGITS
     abat
    0.09
     jacket
    0.08
    Wa
    0.08
     jus
    0.08
    bbox
    0.08
     pats
    0.08
     methane
    0.08
    ային
    0.08
     Jackets
    0.08
     MSD
    0.07
    Activations Density 0.001%

    No Known Activations