© 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. 112388
    Prev
    Next
    INDEX
    Explanations

    use

    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
     tracks
    -0.07
    tracks
    -0.07
    -0.07
    Tracks
    -0.07
     betreffende
    -0.07
     envision
    -0.07
    ಿಎ
    -0.07
    reen
    -0.07
    _tracks
    -0.07
    erta
    -0.07
    POSITIVE LOGITS
     sacs
    0.09
     Scandin
    0.08
     сою
    0.08
     sac
    0.08
     Infinity
    0.08
     synonyms
    0.08
     Samb
    0.08
     kacha
    0.08
    "in
    0.08
    .ir
    0.08
    Activations Density 0.014%
    No Known Activations