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. 60702
    Prev
    Next
    INDEX
    Explanations

    September 11th attacks

    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
    Flower
    -0.09
     flower
    -0.09
    };↵//
    -0.08
    flower
    -0.08
     Flower
    -0.08
     Thickness
    -0.08
     BLO
    -0.07
    ights
    -0.07
     Flowers
    -0.07
    Width
    -0.07
    POSITIVE LOGITS
    .')
    0.08
    /')
    0.08
     acquisitions
    0.08
     alliance
    0.08
     Unlimited
    0.08
     anlay
    0.08
    ghanistan
    0.08
     arsenal
    0.08
     legitimacy
    0.07
     bæði
    0.07
    Activations Density 0.014%

    No Known Activations