© 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. 97626
    Prev
    Next
    INDEX
    Explanations

    �

    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
    参
    -0.07
     billing
    -0.07
    961
    -0.07
    _linear
    -0.07
    971
    -0.07
    سا
    -0.07
    _m
    -0.07
    atit
    -0.07
     distribut
    -0.07
     تطوير
    -0.07
    POSITIVE LOGITS
    枝
    0.14
    �
    0.13
    �
    0.09
    úr
    0.08
    urf
    0.08
     Dubrov
    0.08
    ub
    0.08
     гриб
    0.08
    RAFT
    0.08
     bark
    0.07
    Activations Density 0.001%

    No Known Activations