© 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. 97499
    Prev
    Next
    INDEX
    Explanations

    question

    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
     Midlands
    -0.09
     appunt
    -0.09
    óticos
    -0.08
    psilon
    -0.08
     akwụkwọ
    -0.08
     vogel
    -0.08
     जाना
    -0.08
    ILON
    -0.08
     visiteurs
    -0.08
     Constants
    -0.08
    POSITIVE LOGITS
    naires
    0.20
    naire
    0.19
    -answer
    0.19
     पूछ
    0.18
     answered
    0.17
     posed
    0.15
    Answered
    0.15
     پوچھ
    0.15
     પૂછ
    0.15
     beantworten
    0.15
    Activations Density 0.055%

    No Known Activations