© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110171
    Prev
    Next
    INDEX
    Explanations

    denomin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .chomp
    -0.09
     Assistant
    -0.09
     usher
    -0.08
     Jonathan
    -0.08
     crou
    -0.08
     πάρ
    -0.08
     Half
    -0.08
     grep
    -0.08
    Fila
    -0.08
     Orch
    -0.08
    POSITIVE LOGITS
     валют
    0.15
     currency
    0.13
    _currency
    0.13
     currencies
    0.12
    currency
    0.12
    Currency
    0.12
    .currency
    0.11
     idioma
    0.11
     fiat
    0.11
     langue
    0.11
    Activations Density 0.020%

    No Known Activations