© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 2563
    Prev
    Next
    INDEX
    Explanations

    elemental

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cod
    -0.08
     Cod
    -0.08
    Melissa
    -0.08
    -low
    -0.07
     Adele
    -0.07
    kle
    -0.07
    MESS
    -0.07
     వాట
    -0.07
     bre
    -0.07
    Cod
    -0.07
    POSITIVE LOGITS
    estic
    0.08
    赞
    0.08
    :not
    0.07
    inee
    0.07
     ingr
    0.07
    开的
    0.07
    沉
    0.07
     helps
    0.07
    产
    0.07
     inco
    0.07
    Activations Density 0.001%

    No Known Activations