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. 30058
    Prev
    Next
    INDEX
    Explanations

    Financial accounting

    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
     NF
    -0.09
    271
    -0.07
     Delay
    -0.07
     delay
    -0.07
     בין
    -0.07
    apt
    -0.07
    342
    -0.07
     সু�
    -0.07
    Delay
    -0.07
     nf
    -0.07
    POSITIVE LOGITS
    -total
    0.09
     sash
    0.09
     Transactions
    0.08
    百分
    0.08
     dret
    0.08
     gebeurtenissen
    0.08
     անմ
    0.08
     თვალ
    0.08
    績
    0.08
     interés
    0.08
    Activations Density 0.003%

    No Known Activations