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. 111810
    Prev
    Next
    INDEX
    Explanations

    chemical reactions

    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
    staking
    -0.07
    奏
    -0.07
     endocrine
    -0.07
     belasting
    -0.07
    -padding
    -0.07
     funktioniert
    -0.07
     налог
    -0.07
     Ancient
    -0.07
    %',
    -0.07
     Remodeling
    -0.07
    POSITIVE LOGITS
     ephemeral
    0.13
     fleeting
    0.13
     unstable
    0.12
     volatile
    0.12
     radicals
    0.11
     생성
    0.11
     freshly
    0.10
     Generated
    0.10
     generated
    0.10
     intermedi
    0.10
    Activations Density 0.008%

    No Known Activations