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. 49830
    Prev
    Next
    INDEX
    Explanations

    true

    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
     પરથી
    -0.08
     Vend
    -0.08
    brand
    -0.08
    처럼
    -0.07
     Kev
    -0.07
     Brand
    -0.07
    ap
    -0.07
    _found
    -0.07
     Compiler
    -0.07
    fi
    -0.07
    POSITIVE LOGITS
    且
    0.12
    BUT
    0.09
    /or
    0.08
     அக
    0.08
     BUT
    0.08
    暨
    0.08
    、有
    0.07
     />↵
    0.07
     ஆனால்
    0.07
     То
    0.07
    Activations Density 0.016%

    No Known Activations