© 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. 49103
    Prev
    Next
    INDEX
    Explanations

    Code/Legal Text

    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
    (r
    -0.09
    *r
    -0.08
    -0.07
     Net
    -0.07
    /r
    -0.07
    .as
    -0.07
    _GUID
    -0.07
    $r
    -0.07
    :r
    -0.07
    kennung
    -0.07
    POSITIVE LOGITS
     beige
    0.08
     witch
    0.08
     path
    0.07
     chase
    0.07
    -line
    0.07
     जरूरी
    0.07
     ip
    0.07
     relatos
    0.07
    -story
    0.07
     york
    0.07
    Activations Density 0.006%
    No Known Activations