Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 23418
    Prev
    Next
    INDEX
    Explanations

    Constants

    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
     alors
    -0.08
     assure
    -0.08
    利用
    -0.08
    ,…
    -0.08
     argue
    -0.08
    mt
    -0.08
    uere
    -0.08
     argues
    -0.08
    rare
    -0.08
    dll
    -0.08
    POSITIVE LOGITS
    _THRESHOLD
    0.10
    _INVALID
    0.10
     INVALID
    0.10
     DEFAULT
    0.09
    _EMPTY
    0.09
     Constants
    0.09
    _DEFAULT
    0.09
    _PATH
    0.09
     sentinel
    0.08
    _BASE
    0.08
    Activations Density 0.012%

    No Known Activations