© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 24806
    Prev
    Next
    INDEX
    Explanations

    welcome to the

    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
     photographs
    -0.10
     fotografías
    -0.09
     photographic
    -0.09
    .Foreign
    -0.08
     Offer
    -0.08
     ponud
    -0.08
    ablja
    -0.08
    भर
    -0.08
    (observer
    -0.08
     accred
    -0.08
    POSITIVE LOGITS
     ♪
    0.09
     lite
    0.08
    年度
    0.08
     inyong
    0.08
     �
    0.08
     �
    0.08
     《
    0.08
    XXXX
    0.08
     █
    0.08
     Wonderland
    0.08
    Activations Density 0.047%

    No Known Activations