© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 103157
    Prev
    Next
    INDEX
    Explanations

    cooking pizza

    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
     a
    -0.09
     biodegradable
    -0.09
     part
    -0.08
     in
    -0.08
     small
    -0.08
     standard
    -0.08
     slowed
    -0.08
     pauses
    -0.07
     an
    -0.07
     logic
    -0.07
    POSITIVE LOGITS
     اعلی
    0.11
     hoogste
    0.11
     высокой
    0.11
     mataas
    0.11
     الأحمر
    0.10
     өндөр
    0.10
    SUPERHOST
    0.10
     récent
    0.10
     >=",
    0.10
     მაღალი
    0.10
    Activations Density 0.002%

    No Known Activations