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. 29906
    Prev
    Next
    INDEX
    Explanations

    office environment

    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
    شارك
    -0.09
    _poly
    -0.08
    /post
    -0.07
    شه
    -0.07
    /history
    -0.07
    Streaming
    -0.07
    ева
    -0.07
    携
    -0.07
    (history
    -0.07
    िज
    -0.07
    POSITIVE LOGITS
     prestig
    0.09
     prestigious
    0.09
     RL
    0.08
     nepot
    0.08
    RL
    0.08
    职位
    0.08
    rent
    0.08
    LDAP
    0.08
     работод
    0.08
    秘书
    0.08
    Activations Density 0.002%

    No Known Activations