© 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. 11-RESID-POST-AA
    11. 24595
    Prev
    Next
    INDEX
    Explanations

    pig latin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ભૂ
    -0.09
     thermal
    -0.08
     મહત્વ
    -0.08
    Мат
    -0.08
     કર
    -0.08
    <Resource
    -0.07
    قرار
    -0.07
    怀
    -0.07
    (media
    -0.07
    (torch
    -0.07
    POSITIVE LOGITS
     explan
    0.09
    itions
    0.08
     Alla
    0.08
    onstr
    0.08
     Caesar
    0.08
     puppy
    0.08
     Eus
    0.08
    oys
    0.08
     Handicap
    0.07
     constructions
    0.07
    Activations Density 0.002%

    No Known Activations