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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91633
    Prev
    Next
    INDEX
    Explanations

    of

    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
     commitments
    -0.08
     collisions
    -0.08
     accidents
    -0.08
     ruthless
    -0.08
     Enforcement
    -0.08
     crashing
    -0.07
     badge
    -0.07
     দুর্�
    -0.07
     Collision
    -0.07
     enforcement
    -0.07
    POSITIVE LOGITS
     vowel
    0.15
     vowels
    0.12
    歌
    0.09
     vocalist
    0.09
     accompagné
    0.09
     weich
    0.09
     sung
    0.08
     singing
    0.08
    wuka
    0.08
    柔
    0.08
    Activations Density 0.014%

    No Known Activations