© 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. 11-RESID-POST-AA
    11. 229
    Prev
    Next
    INDEX
    Explanations

    tone

    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
     Amend
    -0.08
     Something
    -0.07
     الخط
    -0.07
    ל
    -0.07
     Sm
    -0.07
     dar
    -0.07
    letcher
    -0.07
     dara
    -0.07
    သူ
    -0.07
     tre
    -0.07
    POSITIVE LOGITS
     tones
    0.11
     tone
    0.10
     calm
    0.10
    -hearted
    0.10
    态
    0.09
     upbeat
    0.09
     toned
    0.09
     �
    0.09
    態
    0.09
     reprim
    0.09
    Activations Density 0.009%

    No Known Activations