© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6493
    Prev
    Next
    INDEX
    Explanations

    Greek letters

    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
    Past
    -0.09
    .cc
    -0.08
    50
    -0.08
    <|endoftext|>
    -0.08
    <|reserved_200016|>
    -0.08
    Patrick
    -0.08
    ('#
    -0.08
    Peers
    -0.08
    19
    -0.08
    "M
    -0.08
    POSITIVE LOGITS
     \
    0.21
     �
    0.18
    �
    0.16
     rho
    0.16
     $\
    0.15
     �
    0.15
    �
    0.15
     phi
    0.15
     sigma
    0.14
     theta
    0.14
    Activations Density 0.225%

    No Known Activations