© 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. 23-RESID-POST-AA
    11. 5923
    Prev
    Next
    INDEX
    Explanations

    Demo

    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
    additional
    -0.11
    actual
    -0.10
    	actual
    -0.10
    organizations
    -0.09
     actual
    -0.09
    _content
    -0.09
    existing
    -0.08
    	data
    -0.08
    organization
    -0.08
    _actual
    -0.08
    POSITIVE LOGITS
     Demo
    0.27
    Demo
    0.26
    -demo
    0.25
    _demo
    0.25
     demo
    0.23
    .demo
    0.22
    demo
    0.21
     Demonstr
    0.16
    -example
    0.16
     Example
    0.16
    Activations Density 0.041%

    No Known Activations