© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 54744
    Prev
    Next
    INDEX
    Explanations

    mortar

    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
    kent
    -0.09
     hostage
    -0.08
     raster
    -0.08
    .serial
    -0.08
    Raster
    -0.07
     shareholder
    -0.07
     Raster
    -0.07
    _serial
    -0.07
     flashes
    -0.07
    .Role
    -0.07
    POSITIVE LOGITS
     milling
    0.10
     Wong
    0.09
     beads
    0.08
     grinding
    0.08
     Milling
    0.08
     قوي
    0.08
     tass
    0.07
     عاج
    0.07
     chants
    0.07
     Manny
    0.07
    Activations Density 0.001%

    No Known Activations