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. 58443
    Prev
    Next
    INDEX
    Explanations

    writing and editing

    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
     predator
    -0.08
     history
    -0.08
    естиваль
    -0.08
    חור
    -0.08
     damal
    -0.07
    启动
    -0.07
    _METADATA
    -0.07
    举办
    -0.07
     Daytona
    -0.07
     cord
    -0.07
    POSITIVE LOGITS
    Sentence
    0.14
     sentences
    0.12
    _sentence
    0.12
    sentence
    0.12
     sentence
    0.12
     readability
    0.12
    を書く
    0.11
     എഴുത
    0.11
     पठ
    0.11
    Writing
    0.11
    Activations Density 0.031%

    No Known Activations