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. 101797
    Prev
    Next
    INDEX
    Explanations

    story 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
    TEL
    -0.09
    _tel
    -0.08
     salvo
    -0.08
    ↵                    ↵
    -0.08
    -${
    -0.08
     систем
    -0.08
    tel
    -0.08
     ${↵
    -0.07
     tel
    -0.07
    _che
    -0.07
    POSITIVE LOGITS
     fuq
    0.08
     Voltage
    0.07
     Watch
    0.07
     بل
    0.07
     Ul
    0.07
    ieg
    0.07
    最新评论
    0.07
     people's
    0.07
     believed
    0.07
     locals
    0.07
    Activations Density 0.113%

    No Known Activations