© 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. 29534
    Prev
    Next
    INDEX
    Explanations

    relaxation techniques

    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
    gebild
    -0.08
    diagram
    -0.08
    (Sprite
    -0.08
    (图
    -0.08
    (video
    -0.08
    排行榜
    -0.08
    加盟
    -0.08
    我国
    -0.08
     sollte
    -0.07
    挂
    -0.07
    POSITIVE LOGITS
     disbelief
    0.09
     Loja
    0.08
     minimalist
    0.08
     spier
    0.08
     nihil
    0.08
     paranoid
    0.08
     skeptical
    0.08
     сом
    0.07
     Muscle
    0.07
     Ske
    0.07
    Activations Density 0.008%

    No Known Activations