© 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. 23-RESID-POST-AA
    11. 50013
    Prev
    Next
    INDEX
    Explanations

    say "peeling"

    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
    سا
    -0.08
    .decorate
    -0.08
    icem
    -0.08
    Mess
    -0.08
     Makes
    -0.07
     construction
    -0.07
     shuts
    -0.07
     Ain
    -0.07
    ạ
    -0.07
     messy
    -0.07
    POSITIVE LOGITS
     fading
    0.12
     peeled
    0.12
     peeling
    0.12
     yellow
    0.11
     flakes
    0.11
     fl
    0.11
     fox
    0.11
     chips
    0.11
    yellow
    0.11
     bubb
    0.11
    Activations Density 0.019%

    No Known Activations