© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78265
    Prev
    Next
    INDEX
    Explanations

    |

    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
    ket
    -0.08
     herbs
    -0.08
     observable
    -0.08
     funnel
    -0.07
     van
    -0.07
     saben
    -0.07
    uenza
    -0.07
     intenz
    -0.07
     vanilla
    -0.07
    定义
    -0.07
    POSITIVE LOGITS
     järgm
    0.10
    �
    0.10
     السادس
    0.09
    ④
    0.09
     الرابعة
    0.08
    ③
    0.08
    十四
    0.08
    第四
    0.08
    14
    0.08
    ⑤
    0.08
    Activations Density 0.036%

    No Known Activations