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. 43136
    Prev
    Next
    INDEX
    Explanations

    =

    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
     skj
    -0.08
    ót
    -0.08
    eret
    -0.07
    แน
    -0.07
     Sommer
    -0.07
     composants
    -0.07
     hidup
    -0.07
    خرج
    -0.07
    TODO
    -0.07
    achat
    -0.07
    POSITIVE LOGITS
     Pau
    0.10
     MASS
    0.08
    Coun
    0.08
    Neighbor
    0.08
     nicer
    0.08
    -pand
    0.08
     pau
    0.07
     suke
    0.07
     lå
    0.07
     dial
    0.07
    Activations Density 0.001%

    No Known Activations