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. 99022
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    endee
    -0.08
    indexed
    -0.08
    >end
    -0.08
    ceptor
    -0.08
    -min
    -0.08
    intent
    -0.08
    enschappelijke
    -0.08
     이후
    -0.08
    -id
    -0.08
    -0.08
    POSITIVE LOGITS
     ترج
    0.10
     translation
    0.10
     tradução
    0.09
    、省
    0.09
    訳
    0.08
     basically
    0.08
     traduction
    0.08
     Tradu
    0.08
     transl
    0.08
     literalmente
    0.08
    Activations Density 0.029%

    No Known Activations