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. 360
    Prev
    Next
    INDEX
    Explanations

    Numbers/Code

    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
     snowy
    -0.09
     Articles
    -0.09
    /wiki
    -0.08
    -Star
    -0.08
     Suitable
    -0.08
     arduous
    -0.08
     Forty
    -0.08
     Mada
    -0.08
     dreadful
    -0.08
     zand
    -0.08
    POSITIVE LOGITS
    ation
    0.08
     that
    0.07
    通
    0.07
     general
    0.07
    st
    0.07
     conf
    0.07
     largest
    0.07
     TC
    0.07
    elho
    0.07
     #
    0.07
    Activations Density 0.000%

    No Known Activations