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. 53079
    Prev
    Next
    INDEX
    Explanations

    world facts

    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
     Rancho
    -0.08
    эн
    -0.08
    .enc
    -0.07
    SER
    -0.07
     sombr
    -0.07
     Parcelable
    -0.07
     쿠
    -0.07
     Hughes
    -0.07
    ນ
    -0.07
     Som
    -0.07
    POSITIVE LOGITS
     سخت
    0.08
     conceivable
    0.07
     relativamente
    0.07
    KP
    0.07
     topl
    0.07
     expressly
    0.07
     outbound
    0.07
     sober
    0.07
     inbound
    0.07
     lucid
    0.07
    Activations Density 0.019%

    No Known Activations