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. 60320
    Prev
    Next
    INDEX
    Explanations

    government and policy

    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
     પ્રમાણે
    -0.09
     odnos
    -0.08
    世界
    -0.08
    ITERAL
    -0.08
     κάθε
    -0.07
     મુજબ
    -0.07
    ுள்ள
    -0.07
     misura
    -0.07
     glowing
    -0.07
    .е
    -0.07
    POSITIVE LOGITS
    /content
    0.09
    /general
    0.09
     जून
    0.08
     Acquisition
    0.08
     verantwort
    0.08
    ؤون
    0.08
    /internal
    0.08
     Communications
    0.08
     mistress
    0.08
     отвечает
    0.08
    Activations Density 0.103%

    No Known Activations