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. 44040
    Prev
    Next
    INDEX
    Explanations

    broad range of topics

    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
    Lit
    -0.08
     pitched
    -0.07
     MLS
    -0.07
    lach
    -0.07
    Possible
    -0.07
    Bat
    -0.07
    WG
    -0.07
     thi
    -0.07
     Jewish
    -0.07
    uaa
    -0.07
    POSITIVE LOGITS
     wissen
    0.08
     kommen
    0.07
    würd
    0.07
     долж
    0.07
     dess
    0.07
     bodily
    0.07
     теле
    0.07
    ديد
    0.07
    bilder
    0.07
     eld
    0.07
    Activations Density 1.042%

    No Known Activations