© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 102561
    Prev
    Next
    INDEX
    Explanations

    is are

    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
     equals
    -0.10
     for
    -0.09
     mitään
    -0.09
    -making
    -0.09
     coincid
    -0.09
    -based
    -0.09
    /man
    -0.09
    /log
    -0.09
     mappings
    -0.08
     imply
    -0.08
    POSITIVE LOGITS
     exquis
    0.10
     recruited
    0.10
     sensitive
    0.09
     notoriously
    0.09
     responsible
    0.09
     Sensitive
    0.09
     highly
    0.09
     renowned
    0.09
     mobile
    0.08
    Sensitive
    0.08
    Activations Density 0.010%

    No Known Activations