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. 45120
    Prev
    Next
    INDEX
    Explanations

    Blueprint

    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
    lomer
    -0.08
    gzip
    -0.08
    gist
    -0.08
     undergone
    -0.08
    digital
    -0.08
     abgeschlossen
    -0.08
     gzip
    -0.08
    gli
    -0.07
     compro
    -0.07
    hann
    -0.07
    POSITIVE LOGITS
     prerequisites
    0.08
     спаль
    0.08
     explic
    0.08
     math
    0.08
     Evel
    0.08
     explicit
    0.08
     maths
    0.07
    wid
    0.07
     asa
    0.07
    Eligibility
    0.07
    Activations Density 0.001%

    No Known Activations