© 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. 96842
    Prev
    Next
    INDEX
    Explanations

    Lists of numbers

    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
     Yi
    -0.08
     prm
    -0.07
     yi
    -0.07
     redistributed
    -0.07
     Monet
    -0.07
    �
    -0.07
    óln
    -0.07
    prep
    -0.07
     mae
    -0.07
     prad
    -0.07
    POSITIVE LOGITS
    115
    0.11
    116
    0.10
    118
    0.08
     encontrada
    0.08
    .Selected
    0.08
    .Protocol
    0.08
    illig
    0.08
    -natural
    0.07
    .selected
    0.07
    .patient
    0.07
    Activations Density 0.002%

    No Known Activations