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. 30134
    Prev
    Next
    INDEX
    Explanations

    non-English language

    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
    itle
    -0.09
     desg
    -0.08
    /she
    -0.08
     substant
    -0.08
     строитель
    -0.08
     cultiv
    -0.08
     Tammy
    -0.07
     clam
    -0.07
     Tin
    -0.07
     worse
    -0.07
    POSITIVE LOGITS
    rd
    0.08
     Xavier
    0.07
    وا
    0.07
    sx
    0.06
     coinc
    0.06
     needed
    0.06
    ோத
    0.06
     mete
    0.06
    sia
    0.06
     blowing
    0.06
    Activations Density 0.007%

    No Known Activations