© 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. 5941
    Prev
    Next
    INDEX
    Explanations

    Chemical measurements

    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
    oseconds
    -0.12
    Seconds
    -0.12
    -beta
    -0.12
    -alpha
    -0.11
     Sekunden
    -0.10
    -ара
    -0.10
     semesters
    -0.10
    _seconds
    -0.10
    -years
    -0.10
    -Shirts
    -0.10
    POSITIVE LOGITS
    kg
    0.12
    mol
    0.12
     kg
    0.12
     molecule
    0.11
     hâ
    0.10
    protein
    0.10
     lâ
    0.10
     yr
    0.10
     mol
    0.10
     kilogram
    0.10
    Activations Density 0.008%

    No Known Activations