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. 130127
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Christophe
    -0.08
     prend
    -0.08
     prennent
    -0.08
     mali
    -0.08
     centres
    -0.07
     Jerry
    -0.07
    Monkey
    -0.07
    ouflage
    -0.07
     Verizon
    -0.07
     Goldco
    -0.07
    POSITIVE LOGITS
    =["
    0.08
     الب
    0.08
    ("")
    0.07
     uds
    0.07
    _ENUM
    0.07
    ാണ്
    0.07
     тя
    0.07
     sly
    0.07
    264
    0.07
    客户端
    0.07
    Activations Density 0.000%

    No Known Activations