Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19003
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فيها
    -0.08
     ثق
    -0.08
     خلالها
    -0.08
     بينها
    -0.08
     نہ
    -0.07
     فيه
    -0.07
     اسم
    -0.07
    Words
    -0.07
     нэр
    -0.07
     stimuleren
    -0.07
    POSITIVE LOGITS
    ਲ
    0.09
     versus
    0.08
     correctly
    0.08
    ਲੀ
    0.08
     korrekt
    0.08
     passer
    0.08
    լ
    0.08
    _vs
    0.08
    alternative
    0.07
     actu
    0.07
    Activations Density 0.005%

    No Known Activations