© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 1466
    Prev
    Next
    INDEX
    Explanations

    –

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     چون
    -0.08
    -0.08
     Ste
    -0.07
    ोस
    -0.07
    emb
    -0.07
    eng
    -0.07
    VIN
    -0.07
    ित्त
    -0.07
    eld
    -0.07
    ive
    -0.07
    POSITIVE LOGITS
     idiot
    0.08
     kcal
    0.07
     Amaz
    0.07
    sar
    0.07
     anon
    0.07
     borderline
    0.07
     promos
    0.07
    ್ವಹ
    0.07
     Cet
    0.07
     divid
    0.07
    Activations Density 0.029%
    No Known Activations