Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 49150
    Prev
    Next
    INDEX
    Explanations

    security warnings

    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
    全天
    -0.08
     escribir
    -0.08
     river
    -0.08
     escribe
    -0.08
     gratitude
    -0.08
    洲
    -0.07
     schreibt
    -0.07
     agradecer
    -0.07
     escrib
    -0.07
     DAY
    -0.07
    POSITIVE LOGITS
     malicious
    0.16
    恶
    0.13
     malware
    0.12
     അപകട
    0.12
    病毒
    0.11
     harmful
    0.11
     зараж
    0.11
     warns
    0.11
     attackers
    0.11
     вред
    0.11
    Activations Density 0.018%

    No Known Activations