© 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. 5410
    Prev
    Next
    INDEX
    Explanations

    �

    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
     XA
    -0.08
    Xa
    -0.08
     chemical
    -0.08
    ok
    -0.08
     chemicals
    -0.08
    _nt
    -0.08
    chemical
    -0.07
     रक्त
    -0.07
    Chemical
    -0.07
    친
    -0.07
    POSITIVE LOGITS
     произвед
    0.08
    zugehen
    0.08
     före
    0.08
     прев
    0.08
     αποτε
    0.08
     исполн
    0.08
     avatars
    0.08
     лид
    0.07
     abond
    0.07
    保障
    0.07
    Activations Density 0.001%

    No Known Activations