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. 77458
    Prev
    Next
    INDEX
    Explanations

    check

    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
     apel
    -0.07
     �
    -0.07
     TSR
    -0.07
    was
    -0.07
    wij
    -0.07
     जाग
    -0.07
     tires
    -0.07
    ખ્ય
    -0.07
     Pense
    -0.07
     tom
    -0.06
    POSITIVE LOGITS
     Kail
    0.10
    ered
    0.08
    Motion
    0.08
    irma
    0.07
     Bol
    0.07
    abla
    0.07
     bè
    0.07
    一下
    0.07
     neu
    0.07
    gra
    0.07
    Activations Density 0.032%

    No Known Activations