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. 9127
    Prev
    Next
    INDEX
    Explanations

    tables

    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
     disproportion
    -0.07
     banal
    -0.07
     UCS
    -0.07
     típica
    -0.07
    달
    -0.07
     kali
    -0.07
     uf
    -0.07
     Dio
    -0.07
    thank
    -0.06
     Kim
    -0.06
    POSITIVE LOGITS
     onbek
    0.13
     неизвест
    0.11
     filled
    0.11
     unknown
    0.11
     desconoc
    0.11
    填写
    0.11
     Fill
    0.11
     Unknown
    0.11
    Fill
    0.10
     rellen
    0.10
    Activations Density 0.026%

    No Known Activations