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. 65095
    Prev
    Next
    INDEX
    Explanations

    physics and relativity

    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
     Biography
    -0.08
    ovanja
    -0.08
     Rein
    -0.07
     vergadering
    -0.07
     Gast
    -0.07
    itures
    -0.07
    Secondly
    -0.07
     Stap
    -0.07
     Resume
    -0.07
     Completable
    -0.07
    POSITIVE LOGITS
    abcdef
    0.08
     fools
    0.08
    ibbons
    0.08
     lis
    0.08
    cionario
    0.08
    liness
    0.08
     idyllic
    0.07
    pread
    0.07
    aisi
    0.07
    abcdefghijklmnopqrstuvwxyz
    0.07
    Activations Density 0.002%

    No Known Activations