© 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. 2657
    Prev
    Next
    INDEX
    Explanations

    -to

    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
     tac
    -0.08
    ancy
    -0.07
     terro
    -0.07
    heid
    -0.07
     ie
    -0.07
    困难
    -0.07
    ificación
    -0.07
     富
    -0.07
     syl
    -0.07
    heen
    -0.07
    POSITIVE LOGITS
    0.08
    �
    0.08
     Designed
    0.08
    નાર
    0.08
    નાં
    0.07
    POWER
    0.07
     દ
    0.07
    ોઝ
    0.07
     olmak
    0.07
    函
    0.07
    Activations Density 0.002%
    No Known Activations