© 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. 15-RESID-POST-AA
    11. 16695
    Prev
    Next
    INDEX
    Explanations

    say "70"

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (=
    -0.08
     Ferry
    -0.08
    calloc
    -0.08
    ują
    -0.08
     courteous
    -0.08
     idem
    -0.07
     Frequent
    -0.07
     Castle
    -0.07
     توسط
    -0.07
    resident
    -0.07
    POSITIVE LOGITS
     FEL
    0.07
    .UTF
    0.07
    .Intent
    0.07
     deeds
    0.07
     KP
    0.07
     leggings
    0.07
     verniet
    0.07
     מא
    0.07
     skulle
    0.07
     absolute
    0.07
    Activations Density 0.000%

    No Known Activations