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. 59076
    Prev
    Next
    INDEX
    Explanations

    2

    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
     acog
    -0.08
     acomod
    -0.08
     glück
    -0.08
     humiliation
    -0.08
    �
    -0.08
    abag
    -0.08
     jail
    -0.08
     Comunicación
    -0.08
     الاحت
    -0.08
    _boot
    -0.08
    POSITIVE LOGITS
     derivative
    0.10
    Derivative
    0.08
     derivatives
    0.08
    ీస్
    0.07
    <!--
    0.07
    ిస్
    0.07
     dominate
    0.07
    יתים
    0.07
    ీల
    0.07
    licer
    0.07
    Activations Density 0.048%

    No Known Activations