© 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. 47524
    Prev
    Next
    INDEX
    Explanations

    smoke

    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
     taxable
    -0.08
     backlink
    -0.08
    hten
    -0.08
     lucrative
    -0.08
    一码
    -0.08
     freelancer
    -0.08
     eenvoudige
    -0.08
     simpele
    -0.07
    (simple
    -0.07
     gampang
    -0.07
    POSITIVE LOGITS
     дым
    0.12
    烟
    0.11
    煙
    0.11
     inhal
    0.11
     और
    0.10
     и
    0.10
     and
    0.10
     اور
    0.10
     ಮತ್ತು
    0.10
     এবং
    0.10
    Activations Density 0.007%

    No Known Activations