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. 45086
    Prev
    Next
    INDEX
    Explanations

    v

    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
    (Math
    -0.08
     intervent
    -0.08
     entrusted
    -0.08
     Tacoma
    -0.07
    .pull
    -0.07
     widespread
    -0.07
     Ron
    -0.07
     BCM
    -0.07
    민
    -0.07
     dziś
    -0.07
    POSITIVE LOGITS
    ాకు
    0.09
     קוק
    0.08
     nuis
    0.08
    大战
    0.08
     �
    0.08
     בצורה
    0.08
     вида
    0.07
     saut
    0.07
     abruptly
    0.07
     nucléaire
    0.07
    Activations Density 0.004%

    No Known Activations