© 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. 48562
    Prev
    Next
    INDEX
    Explanations

    say "streams"

    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
    Dispose
    -0.08
    <unsigned
    -0.08
    	property
    -0.08
    (property
    -0.08
     disposal
    -0.08
    ƒ
    -0.08
    Redux
    -0.08
    <boolean
    -0.08
    	BOOL
    -0.08
     dissip
    -0.07
    POSITIVE LOGITS
     Stream
    0.20
     Streams
    0.19
     Collections
    0.18
     Collection
    0.18
     Scanner
    0.18
     Optional
    0.16
     streams
    0.16
     Apache
    0.15
    _stream
    0.15
     List
    0.15
    Activations Density 0.018%

    No Known Activations