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. 60952
    Prev
    Next
    INDEX
    Explanations

    Mathematical expressions

    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
    /octet
    -0.08
     HDR
    -0.08
     richer
    -0.07
    \\/
    -0.07
    liefer
    -0.07
    침
    -0.07
     verlassen
    -0.07
     raft
    -0.07
     ports
    -0.07
     thì
    -0.07
    POSITIVE LOGITS
    _equals
    0.08
     Aut
    0.08
     लोगों
    0.08
     egész
    0.08
     张
    0.08
     Exam
    0.08
     Apartment
    0.08
     gesprek
    0.07
    0.07
     Equality
    0.07
    Activations Density 0.031%

    No Known Activations