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

    Neuronpedia

    APICircuit 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. 43912
    Prev
    Next
    INDEX
    Explanations

    code/math snippets

    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
    ';
    -0.08
    .’
    -0.08
    ']↵↵
    -0.08
    ];
    -0.08
    項
    -0.07
    TACT
    -0.07
    ';↵↵
    -0.07
    .]
    -0.07
    项
    -0.07
    .]↵↵
    -0.07
    POSITIVE LOGITS
    êle
    0.08
     criatura
    0.08
     организма
    0.08
     creature
    0.08
    _UN
    0.08
     kropp
    0.08
    bereiche
    0.08
     criaturas
    0.08
     kerül
    0.08
     lichaam
    0.08
    Activations Density 0.114%

    No Known Activations