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. 58532
    Prev
    Next
    INDEX
    Explanations

    need

    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
    @hotmail
    -0.09
     Wehr
    -0.08
    wort
    -0.08
     reutil
    -0.08
    @yahoo
    -0.08
    @Target
    -0.08
    oubt
    -0.07
    �
    -0.07
     clips
    -0.07
    Clip
    -0.07
    POSITIVE LOGITS
     ари
    0.09
     בע
    0.09
    keningen
    0.09
     계산
    0.09
     قوان
    0.08
     fictional
    0.08
    Scenario
    0.08
     गण
    0.08
     arithmetic
    0.08
     രണ്ടു
    0.08
    Activations Density 0.066%

    No Known Activations