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. 113863
    Prev
    Next
    INDEX
    Explanations

    Pro

    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
    genomen
    -0.08
     antecedentes
    -0.08
    };↵↵↵↵
    -0.07
    Ellipse
    -0.07
     };
    -0.07
     };↵
    -0.07
    .Identity
    -0.07
    .Distance
    -0.07
    .location
    -0.07
    POSITIVE LOGITS
     bij
    0.12
     pairing
    0.09
     counting
    0.09
    bije
    0.09
     counted
    0.09
    Counting
    0.09
     Counting
    0.09
     togg
    0.09
     kontrib
    0.08
    _swap
    0.08
    Activations Density 0.028%

    No Known Activations