© 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. 11-RESID-POST-AA
    11. 54887
    Prev
    Next
    INDEX
    Explanations

    GSM

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dama
    -0.10
     plunge
    -0.08
     Rosie
    -0.08
     prune
    -0.08
    λία
    -0.08
     kos
    -0.08
     plunged
    -0.08
     bals
    -0.08
    玉
    -0.08
    াদক
    -0.08
    POSITIVE LOGITS
     encrypted
    0.10
    Studies
    0.09
     estudar
    0.07
     estudiar
    0.07
    OVA
    0.07
     উপস্থিত
    0.07
     studies
    0.07
    ebol
    0.07
     MHz
    0.07
    sab
    0.07
    Activations Density 0.003%

    No Known Activations