© 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. 19-RESID-POST-AA
    11. 102546
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pelle
    -0.07
     **
    -0.07
     '(
    -0.07
    oncer
    -0.07
     True
    -0.07
     quadr
    -0.07
     SUNNY
    -0.07
     true
    -0.07
    'ensemble
    -0.07
    bildungs
    -0.07
    POSITIVE LOGITS
     avonds
    0.10
    .shutdown
    0.10
    .logout
    0.10
     deadlines
    0.10
     അവസാന
    0.10
    晚
    0.10
     siste
    0.10
    últ
    0.10
     evenings
    0.10
     shutting
    0.10
    Activations Density 0.011%

    No Known Activations