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. 30497
    Prev
    Next
    INDEX
    Explanations

    定位

    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
    lada
    -0.08
     gere
    -0.07
     strategically
    -0.07
     piled
    -0.07
    🏼
    -0.07
    aps
    -0.07
     Portug
    -0.07
    akala
    -0.07
     coag
    -0.07
     Planned
    -0.07
    POSITIVE LOGITS
     cuánto
    0.08
     niche
    0.08
     Needle
    0.08
    Locate
    0.08
     locating
    0.08
    _LOCATION
    0.08
    ierungs
    0.08
    まり
    0.08
     niches
    0.08
     vain
    0.08
    Activations Density 0.012%

    No Known Activations