© 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. 68103
    Prev
    Next
    INDEX
    Explanations

    deterministic

    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
    park
    -0.08
     Diskussion
    -0.08
    curité
    -0.08
    措
    -0.08
     energet
    -0.08
     Tale
    -0.07
    google
    -0.07
    hrase
    -0.07
     organically
    -0.07
     Anniversary
    -0.07
    POSITIVE LOGITS
     deterministic
    0.18
     determin
    0.13
     predictable
    0.09
     निर्ध
    0.09
     certainty
    0.09
     predict
    0.09
    etermin
    0.08
     founder
    0.08
     previs
    0.07
     சார
    0.07
    Activations Density 0.007%

    No Known Activations