© 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. 103551
    Prev
    Next
    INDEX
    Explanations

    crimes

    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
     Legislativo
    -0.11
    ähler
    -0.09
     Juríd
    -0.09
    ijakan
    -0.08
    .~
    -0.08
    .Invariant
    -0.08
    -Founder
    -0.08
    ocene
    -0.08
     Cooler
    -0.08
     Gobierno
    -0.08
    POSITIVE LOGITS
     robbery
    0.13
     burglary
    0.13
     kidnapping
    0.12
    強奸
    0.12
     homicide
    0.12
     assault
    0.12
     adul
    0.12
     murder
    0.11
     possession
    0.11
     aggravated
    0.11
    Activations Density 0.023%

    No Known Activations