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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RESID-POST-AA
    11. 113304
    Prev
    Next
    INDEX
    Explanations

    Histone modifications

    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
    <a
    -0.09
    "d
    -0.09
    <x
    -0.08
    <strong
    -0.08
    <O
    -0.08
    Transmission
    -0.08
    "M
    -0.08
    -ka
    -0.08
    (<
    -0.07
    "a
    -0.07
    POSITIVE LOGITS
     Albion
    0.08
    ALK
    0.08
     sklearn
    0.08
     ή
    0.08
     skyline
    0.07
     سك
    0.07
     hemisphere
    0.07
     Gir
    0.07
    ลี
    0.07
     lys
    0.07
    Activations Density 0.001%

    No Known Activations