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. 77577
    Prev
    Next
    INDEX
    Explanations

    coloring

    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
     jang
    -0.07
    �
    -0.07
     offering
    -0.07
     plais
    -0.07
    农村
    -0.07
     ekonomik
    -0.07
     agrad
    -0.07
    ಂದ
    -0.07
     virtues
    -0.07
     (;
    -0.07
    POSITIVE LOGITS
    quen
    0.08
     pinch
    0.08
     puder
    0.08
    umbre
    0.08
    =document
    0.08
     potion
    0.08
     hue
    0.08
    Hue
    0.08
     customizing
    0.08
     mayonnaise
    0.08
    Activations Density 0.007%

    No Known Activations