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. 112818
    Prev
    Next
    INDEX
    Explanations

    code prompts

    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
     clinker
    -0.09
     enclave
    -0.09
     cloak
    -0.08
     скла
    -0.08
    arest
    -0.08
    ensic
    -0.08
    thest
    -0.08
    _layers
    -0.08
     доказ
    -0.08
    .layers
    -0.08
    POSITIVE LOGITS
     prompts
    0.18
     prompting
    0.15
    提示
    0.14
     안내
    0.13
    .prompt
    0.13
     приглаш
    0.12
    prompt
    0.12
     cues
    0.11
    _prompt
    0.11
     invita
    0.11
    Activations Density 0.013%

    No Known Activations