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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19146
    Prev
    Next
    INDEX
    Explanations

    pi

    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
     ###
    -0.08
     temps
    -0.08
    fiction
    -0.08
     enfrentar
    -0.07
    halten
    -0.07
     fiction
    -0.07
    ساعد
    -0.07
    .selenium
    -0.07
     ficción
    -0.07
    셜
    -0.07
    POSITIVE LOGITS
    洲
    0.08
    cases
    0.07
    の場合
    0.07
    ρ
    0.07
     vet
    0.07
    {}
    0.07
     دلار
    0.07
    /(
    0.07
    course
    0.07
     אינו
    0.07
    Activations Density 0.010%

    No Known Activations