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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 19122
    Prev
    Next
    INDEX
    Explanations

    say "v" and down arrow

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ()].
    -0.09
    ।”↵↵
    -0.09
    .”↵↵
    -0.09
     accomplishments
    -0.09
    ].↵↵
    -0.09
     instructions
    -0.09
     accomplishing
    -0.09
    :index
    -0.09
    ।↵↵
    -0.09
    ۔↵↵
    -0.09
    POSITIVE LOGITS
     ▼
    0.18
     v
    0.16
    	v
    0.15
     V
    0.15
    ▼
    0.13
    V
    0.13
    v
    0.12
    	V
    0.12
     ↓
    0.12
     VStack
    0.11
    Activations Density 0.003%

    No Known Activations