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. 43592
    Prev
    Next
    INDEX
    Explanations

    corn

    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
     instellingen
    -0.08
     diffic
    -0.08
     instelling
    -0.08
     paradig
    -0.07
    ological
    -0.07
    ria
    -0.07
    ividual
    -0.07
     ingesteld
    -0.07
    ficos
    -0.07
    _module
    -0.07
    POSITIVE LOGITS
     Север
    0.08
     picked
    0.08
     ụtọ
    0.08
     Picks
    0.08
     picks
    0.07
     груди
    0.07
     SIX
    0.07
    -Tr
    0.07
     mochten
    0.07
     карти
    0.07
    Activations Density 0.001%

    No Known Activations