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. 130373
    Prev
    Next
    INDEX
    Explanations

    sensory writing

    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
    Unary
    -0.08
     Unary
    -0.08
    ATION
    -0.08
    ్
    -0.08
    task
    -0.07
    -dé
    -0.07
     tareas
    -0.07
    aru
    -0.07
     Generally
    -0.07
    ್
    -0.07
    POSITIVE LOGITS
     immersive
    0.12
     vivid
    0.12
     vividly
    0.12
     vivido
    0.12
     firsthand
    0.12
     ощущ
    0.10
    现场
    0.10
     അനു�
    0.10
     രംഗ
    0.10
     உண
    0.09
    Activations Density 0.044%

    No Known Activations