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. 11-RESID-POST-AA
    6. 120436
    Prev
    Next
    INDEX
    Explanations

    technical specifications

    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
    ル
    -0.07
     Ipsum
    -0.07
    уды
    -0.07
    yeurs
    -0.07
     �
    -0.07
    cp
    -0.07
    _utils
    -0.07
     सहित
    -0.07
     Kop
    -0.07
     पड़े
    -0.07
    POSITIVE LOGITS
    Mostly
    0.08
    .TIM
    0.07
    schrift
    0.07
     प्रतिभ
    0.07
    ™,
    0.07
     graft
    0.07
    oftware
    0.07
    _MOD
    0.07
     temperatuur
    0.07
    币
    0.07
    Activations Density 0.062%

    No Known Activations