© 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. 48168
    Prev
    Next
    INDEX
    Explanations

    say "the ending ies/iesa"

    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
    -browser
    -0.08
     nla
    -0.08
    -security
    -0.08
    സ്സ
    -0.08
     Nik
    -0.08
    സ
    -0.07
    セ
    -0.07
    -family
    -0.07
     associative
    -0.07
     sesso
    -0.07
    POSITIVE LOGITS
    ICES
    0.08
     Tac
    0.08
     jas
    0.08
     gbc
    0.07
     вал
    0.07
    ierz
    0.07
    lashes
    0.07
    ABB
    0.07
    Tac
    0.07
    hera
    0.07
    Activations Density 0.000%

    No Known Activations