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. 352
    Prev
    Next
    INDEX
    Explanations

    Trapped under something

    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
     connex
    -0.10
    连接
    -0.08
    tery
    -0.08
     connected
    -0.08
     connecting
    -0.07
    _connections
    -0.07
     connections
    -0.07
    conn
    -0.07
    acteria
    -0.07
     coordinator
    -0.07
    POSITIVE LOGITS
     overwhelmed
    0.11
     esmag
    0.11
     piled
    0.11
     overwhel
    0.11
     overturned
    0.11
     سحق
    0.11
    압
    0.11
     shove
    0.10
    Pile
    0.10
     سقوط
    0.10
    Activations Density 0.069%

    No Known Activations