© 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. 1405
    Prev
    Next
    INDEX
    Explanations

    NTR

    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
     tane
    -0.08
     Watson
    -0.08
     اللہ
    -0.08
     항
    -0.08
     �
    -0.07
     bellen
    -0.07
    untungan
    -0.07
     denomin
    -0.07
     Alle
    -0.07
     Uf
    -0.07
    POSITIVE LOGITS
    ysical
    0.08
    ider
    0.08
    DEX
    0.07
     EMT
    0.07
    acting
    0.07
    actable
    0.07
    HAV
    0.07
     midnight
    0.07
    jde
    0.07
    urface
    0.07
    Activations Density 0.001%

    No Known Activations