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. 12647
    Prev
    Next
    INDEX
    Explanations

    VLOOKUP excel function

    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
     Egg
    -0.07
    -poly
    -0.07
    culpt
    -0.07
    .New
    -0.07
    全民
    -0.07
     underpin
    -0.07
     ਬਣ
    -0.07
    'énergie
    -0.07
     Dej
    -0.07
     rejuven
    -0.07
    POSITIVE LOGITS
     сосед
    0.11
    附近
    0.10
     அருக
    0.10
     nearest
    0.09
     neighbors
    0.09
     അടുത്ത
    0.09
    距离
    0.09
     locating
    0.09
     값을
    0.09
     INDIRECT
    0.09
    Activations Density 0.005%

    No Known Activations