© 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. 23-RESID-POST-AA
    11. 6561
    Prev
    Next
    INDEX
    Explanations

    Unusual characters/formulas

    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
    564
    -0.10
     seventh
    -0.10
     fifty
    -0.09
    04
    -0.09
     seven
    -0.09
    577
    -0.09
    ств
    -0.09
    566
    -0.09
     sixth
    -0.09
     Fifty
    -0.09
    POSITIVE LOGITS
    Γ
    0.09
    Ф
    0.08
    umni
    0.08
    γει
    0.08
    ఫ
    0.08
    329
    0.08
    Banner
    0.08
    GL
    0.08
    Λ
    0.08
    ファ
    0.08
    Activations Density 0.123%

    No Known Activations