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. 30221
    Prev
    Next
    INDEX
    Explanations

    plausible, fabricated information

    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
     Nyt
    -0.08
     repl
    -0.07
    Whitespace
    -0.07
     nyt
    -0.07
     simultaneous
    -0.07
    ;t
    -0.07
    Constructor
    -0.07
     Plates
    -0.07
    �
    -0.06
    Code
    -0.06
    POSITIVE LOGITS
     fict
    0.21
     fictional
    0.21
     invented
    0.17
     pretend
    0.17
     hypothetical
    0.16
     plausible
    0.16
     pretending
    0.16
    fiction
    0.15
    是假
    0.15
    假的
    0.15
    Activations Density 0.119%

    No Known Activations