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. 3-RESID-POST-AA
    6. 2046
    Prev
    Next
    INDEX
    Explanations

    Code and numerical analysis

    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
     Katz
    -0.09
     suc
    -0.08
     wander
    -0.08
     cooler
    -0.08
    ింది
    -0.08
    778
    -0.07
     unf
    -0.07
     Wad
    -0.07
    Cool
    -0.07
     inward
    -0.07
    POSITIVE LOGITS
     Gov
    0.09
     Wy
    0.09
     Roy
    0.08
     Shah
    0.08
     മേ
    0.07
     மே
    0.07
     Hr
    0.07
     damp
    0.07
     Tamp
    0.07
    pret
    0.07
    Activations Density 0.095%

    No Known Activations