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. 129760
    Prev
    Next
    INDEX
    Explanations

    translation

    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
     large
    -0.08
     लाइ
    -0.07
     गोल
    -0.07
     Fortune
    -0.07
     selectable
    -0.07
     LIB
    -0.07
     progress
    -0.07
     zot
    -0.07
     números
    -0.07
     caz
    -0.07
    POSITIVE LOGITS
     traduz
    0.13
    translate
    0.11
     translate
    0.11
     traduc
    0.11
     traduit
    0.11
     tradução
    0.10
    Translated
    0.10
     Originally
    0.10
     translates
    0.10
    Translate
    0.10
    Activations Density 0.046%

    No Known Activations