© 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. 23-RESID-POST-AA
    11. 6028
    Prev
    Next
    INDEX
    Explanations

    powin

    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
    lace
    -0.08
    uos
    -0.08
    ч
    -0.07
     chem
    -0.07
    auch
    -0.07
    adora
    -0.07
    し
    -0.07
    化
    -0.07
    .loc
    -0.07
    uot
    -0.07
    POSITIVE LOGITS
    ien
    0.12
    iene
    0.10
    entliche
    0.10
    ienes
    0.10
    entlich
    0.09
    ίνεται
    0.09
     тиіс
    0.09
     להיות
    0.09
    lgende
    0.09
     Iso
    0.09
    Activations Density 0.001%

    No Known Activations