© 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. 47878
    Prev
    Next
    INDEX
    Explanations

    metals

    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
    ייפ
    -0.09
    hrif
    -0.08
     tanks
    -0.08
    .FILL
    -0.08
     camping
    -0.08
     स्टेशन
    -0.08
    unge
    -0.08
     פּראָ
    -0.08
     microorgan
    -0.08
    יווק
    -0.08
    POSITIVE LOGITS
     copper
    0.11
     nickel
    0.10
     lead
    0.10
     lithium
    0.10
     platinum
    0.10
     silver
    0.09
     precious
    0.09
     zinc
    0.09
     Lead
    0.09
     cuivre
    0.09
    Activations Density 0.012%

    No Known Activations