© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 29740
    Prev
    Next
    INDEX
    Explanations

    geography landscapes locations

    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
    Persona
    -0.09
    persona
    -0.09
     persona
    -0.09
     Persona
    -0.08
    opcode
    -0.08
     Zustimmung
    -0.08
     ethical
    -0.08
     IBM
    -0.08
    消费
    -0.08
     unethical
    -0.08
    POSITIVE LOGITS
    terrain
    0.14
     vegetation
    0.14
     terrain
    0.13
     Terrain
    0.13
    坡
    0.12
     terraces
    0.12
     landscaping
    0.12
    面积
    0.12
     scenic
    0.12
     creek
    0.12
    Activations Density 0.093%

    No Known Activations