© 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. 19-RESID-POST-AA
    11. 103181
    Prev
    Next
    INDEX
    Explanations

    protein

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Walking
    -0.09
    walking
    -0.09
    Walking
    -0.09
    wohn
    -0.08
     നടക്ക
    -0.08
     tokko
    -0.08
    ideen
    -0.08
     bullying
    -0.08
     walking
    -0.08
     exposing
    -0.08
    POSITIVE LOGITS
    _s
    0.12
     sínt
    0.11
     synthesis
    0.11
    _ip
    0.09
     synthesized
    0.09
     sumi
    0.09
     surname
    0.09
    _db
    0.09
     sintet
    0.09
     sün
    0.09
    Activations Density 0.001%

    No Known Activations