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. 102590
    Prev
    Next
    INDEX
    Explanations

    Dialogue

    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
     beg
    -0.07
    yssey
    -0.07
     સુધી
    -0.07
    rifice
    -0.07
     jobb
    -0.07
     cursed
    -0.07
    -0.07
     brink
    -0.07
    以后
    -0.07
     okuy
    -0.07
    POSITIVE LOGITS
     Navbar
    0.09
    .refresh
    0.09
    *[
    0.08
     refreshing
    0.08
    FFA
    0.08
    Morning
    0.08
    *S
    0.08
    -Feb
    0.08
     പഴ
    0.08
    Refreshing
    0.08
    Activations Density 0.012%

    No Known Activations