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. 113942
    Prev
    Next
    INDEX
    Explanations

    Cassandra

    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
     computerized
    -0.09
     Cabinet
    -0.08
     ejecutivo
    -0.08
    ांकन
    -0.08
     virtualization
    -0.08
     door
    -0.08
    -0.08
     generous
    -0.08
     lodash
    -0.08
     completo
    -0.07
    POSITIVE LOGITS
     surfer
    0.08
     VLAN
    0.08
    .xpath
    0.08
     мощ
    0.07
     Bour
    0.07
     cabel
    0.07
     ker
    0.07
     MHz
    0.07
     tetr
    0.07
    ystal
    0.07
    Activations Density 0.001%

    No Known Activations