© 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. 19-RESID-POST-AA
    11. 102211
    Prev
    Next
    INDEX
    Explanations

    atoms and oxygen

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iculture
    -0.09
     acl
    -0.08
     tə
    -0.08
     Cabinet
    -0.08
    Taxi
    -0.08
    MSG
    -0.08
    acad
    -0.08
     cassino
    -0.08
     shampo
    -0.08
     MMORPG
    -0.08
    POSITIVE LOGITS
     Oxygen
    0.16
     oxygen
    0.16
     atoms
    0.14
    oxygen
    0.12
    _atoms
    0.12
     атом
    0.11
     nitrogen
    0.11
    atoms
    0.11
     electrons
    0.10
    氧
    0.10
    Activations Density 0.009%

    No Known Activations