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. 56229
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
     taart
    -0.09
     संत
    -0.09
     추진
    -0.08
    kolog
    -0.08
     terraform
    -0.08
    青草
    -0.08
     पर्व
    -0.08
     malas
    -0.08
     Terraform
    -0.08
     champion
    -0.08
    POSITIVE LOGITS
     linguistic
    0.15
     lingü
    0.13
     pronunciation
    0.13
     Lingu
    0.13
     Vocabulary
    0.12
     lingua
    0.12
     langue
    0.12
     மொழ
    0.11
    乱码
    0.11
    .Language
    0.11
    Activations Density 0.037%

    No Known Activations