© 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. 48786
    Prev
    Next
    INDEX
    Explanations

    of

    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
     habitantes
    -0.11
     yaşayan
    -0.10
     viviendo
    -0.09
    参加
    -0.09
     Participation
    -0.09
     participation
    -0.09
     practicing
    -0.08
    েঁ
    -0.08
    ότητα
    -0.08
     inwoners
    -0.08
    POSITIVE LOGITS
     wrongdoing
    0.18
     violent
    0.17
     незакон
    0.13
     harmful
    0.12
     terrorist
    0.11
     crimes
    0.11
     unlawful
    0.11
     Acts
    0.11
     malware
    0.10
    violent
    0.10
    Activations Density 0.007%

    No Known Activations