© 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. 30100
    Prev
    Next
    INDEX
    Explanations

    status

    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
     volley
    -0.08
     Zab
    -0.08
     insults
    -0.08
     Rift
    -0.08
     insult
    -0.08
     retaliation
    -0.08
     зеркало
    -0.08
    iid
    -0.08
     Busch
    -0.07
    .divide
    -0.07
    POSITIVE LOGITS
    =status
    0.13
     statuses
    0.13
     status
    0.12
    	Status
    0.12
    (status
    0.12
     Status
    0.12
    状态
    0.12
    	status
    0.11
    Status
    0.11
    >Status
    0.11
    Activations Density 0.013%

    No Known Activations