© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RESID-POST-AA
    11. 69872
    Prev
    Next
    INDEX
    Explanations

    Dialogues and narratives

    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
     Gewer
    -0.08
     deriving
    -0.08
     analogous
    -0.08
     constructing
    -0.08
    stemming
    -0.08
    470
    -0.08
     paralle
    -0.08
     Hirsch
    -0.08
    ≥
    -0.08
     inch
    -0.08
    POSITIVE LOGITS
     정말
    0.09
    _ALREADY
    0.08
     Causes
    0.08
    ...”
    0.08
    ...</
    0.08
     unnoticed
    0.08
     alright
    0.08
     ridiculous
    0.08
     cosplay
    0.08
     GOT
    0.08
    Activations Density 0.031%

    No Known Activations