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. 9096
    Prev
    Next
    INDEX
    Explanations

    mathematics

    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
     אלו
    -0.08
    amps
    -0.08
     AM
    -0.07
     am
    -0.07
     दे
    -0.07
    161
    -0.07
     lateral
    -0.07
    ールド
    -0.07
    _MODULE
    -0.07
    .pm
    -0.07
    POSITIVE LOGITS
    -là
    0.19
     ...↵↵↵
    0.08
    ,该
    0.08
    Ral
    0.08
     대해
    0.08
     longe
    0.07
     પહોંચી
    0.07
     gewesen
    0.07
    ertung
    0.07
     pewno
    0.07
    Activations Density 0.173%

    No Known Activations