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. 11-RESID-POST-AA
    6. 53196
    Prev
    Next
    INDEX
    Explanations

    GET

    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
     Hak
    -0.08
    /or
    -0.08
     Ky
    -0.08
     kuko
    -0.07
    �
    -0.07
    ಣದಲ್ಲಿ
    -0.07
     التلف
    -0.07
    olland
    -0.07
     possible
    -0.07
    返
    -0.07
    POSITIVE LOGITS
    BAN
    0.08
     ясно
    0.07
     ең
    0.07
     ən
    0.07
     bästa
    0.07
     கிட
    0.07
    EP
    0.07
    итай
    0.07
     બે
    0.07
     pinakamahusay
    0.07
    Activations Density 0.001%

    No Known Activations