© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 96809
    Prev
    Next
    INDEX
    Explanations

    New

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chip
    -0.08
     саб
    -0.08
     dalk
    -0.08
     BAL
    -0.08
     CO
    -0.08
    chip
    -0.08
     Chip
    -0.08
    Bal
    -0.08
    Chip
    -0.07
     chicos
    -0.07
    POSITIVE LOGITS
     testament
    0.19
     Testament
    0.17
    -test
    0.10
    -Test
    0.10
     Covenant
    0.10
     Jerusalem
    0.10
     covenant
    0.10
     World
    0.09
     embodiment
    0.09
     heavens
    0.09
    Activations Density 0.005%

    No Known Activations