© 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. 49172
    Prev
    Next
    INDEX
    Explanations

    included

    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
     It's
    -0.13
    It's
    -0.12
     it's
    -0.11
     Are
    -0.11
    it's
    -0.11
    удың
    -0.11
     they're
    -0.10
    ，我们
    -0.10
    —is
    -0.10
     we
    -0.10
    POSITIVE LOGITS
     included
    0.25
     Included
    0.23
    included
    0.23
    Included
    0.21
     ensured
    0.20
     inbegrepen
    0.19
     noted
    0.19
     retained
    0.19
     vorhanden
    0.18
     möglich
    0.18
    Activations Density 0.316%

    No Known Activations