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. 29959
    Prev
    Next
    INDEX
    Explanations

    easily

    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
     đất
    -0.08
     kissed
    -0.08
     inception
    -0.08
    室
    -0.08
     tonne
    -0.07
     fondamentale
    -0.07
    кір
    -0.07
    piel
    -0.07
    chi
    -0.07
     Peninsula
    -0.07
    POSITIVE LOGITS
     enough
    0.08
     consegu
    0.08
     heuristic
    0.08
     grasp
    0.08
     IOError
    0.08
     Jay
    0.07
     inexp
    0.07
     dàng
    0.07
     Tib
    0.07
     आसानी
    0.07
    Activations Density 0.017%

    No Known Activations