© 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. 23-RESID-POST-AA
    11. 97350
    Prev
    Next
    INDEX
    Explanations

    Code snippets/prompts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Recording
    -0.08
     judiciaire
    -0.07
    .layers
    -0.07
     erected
    -0.07
     asos
    -0.07
     erect
    -0.07
     Montage
    -0.07
    над
    -0.07
     Upgrade
    -0.07
     recording
    -0.07
    POSITIVE LOGITS
    interp
    0.09
     oct
    0.09
    omp
    0.08
    FEB
    0.08
     OCT
    0.08
     BOT
    0.08
    ossa
    0.08
    Portugal
    0.07
    oct
    0.07
    Interp
    0.07
    Activations Density 0.000%

    No Known Activations