Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 120345
    Prev
    Next
    INDEX
    Explanations

    from

    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
     tę
    -0.08
     determining
    -0.08
    onor
    -0.08
     peril
    -0.08
    ily
    -0.08
     crossing
    -0.07
    ATP
    -0.07
     speaking
    -0.07
     accru
    -0.07
    ทุก
    -0.07
    POSITIVE LOGITS
     Mann
    0.09
     faker
    0.08
    _executor
    0.08
     Edwards
    0.08
    朋友
    0.08
    orme
    0.07
     apologies
    0.07
    ச
    0.07
     sklearn
    0.07
    _wallet
    0.07
    Activations Density 0.002%

    No Known Activations