Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90489
    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_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HVAC
    -0.09
     MEDIATEK
    -0.08
    \s
    -0.08
     Greenland
    -0.08
     часу
    -0.08
     nche
    -0.07
     ngx
    -0.07
     WWII
    -0.07
    iptir
    -0.07
    ображ
    -0.07
    POSITIVE LOGITS
    passt
    0.10
     substit
    0.09
     substitute
    0.08
     fullness
    0.08
    Dao
    0.08
    SI
    0.08
    wat
    0.07
     rational
    0.07
     eliminates
    0.07
    Sha
    0.07
    Activations Density 0.048%

    No Known Activations