© 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. 97636
    Prev
    Next
    INDEX
    Explanations

    say "over"

    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
     النوم
    -0.09
     Tempor
    -0.09
     tijdelijk
    -0.08
     temporary
    -0.08
    izare
    -0.08
     الروا
    -0.08
     Temporary
    -0.08
    vuldig
    -0.08
    aitheamh
    -0.08
    暂
    -0.08
    POSITIVE LOGITS
     uncovered
    0.13
     covered
    0.11
     unloaded
    0.10
    Covered
    0.10
    covered
    0.10
     около
    0.09
     tossed
    0.09
     und
    0.09
     upright
    0.09
     coated
    0.09
    Activations Density 0.015%

    No Known Activations