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. 111695
    Prev
    Next
    INDEX
    Explanations

    spontaneous

    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
     Yoh
    -0.08
    ову
    -0.08
    jug
    -0.07
    endum
    -0.07
     engager
    -0.07
     Athletics
    -0.07
    oard
    -0.07
     nadr
    -0.07
     bes
    -0.07
     modifying
    -0.07
    POSITIVE LOGITS
     espont
    0.12
     spont
    0.10
     goodwill
    0.09
     spontaneously
    0.09
     spontane
    0.08
    想到
    0.08
     spontaneous
    0.08
    aneously
    0.08
     gask
    0.08
     Gilbert
    0.08
    Activations Density 0.002%

    No Known Activations