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. 44856
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
     તેથી
    -0.09
     Certaines
    -0.09
    。但是
    -0.09
    。因此
    -0.09
     많
    -0.08
    Также
    -0.08
    %x
    -0.08
     Dusche
    -0.08
     이를
    -0.08
    。所以
    -0.08
    POSITIVE LOGITS
     -*-
    0.08
     ----------------------------------------------------------------
    0.08
     ------------------------------------------------
    0.08
     Google's
    0.07
     NOTE
    0.07
     Check
    0.07
     സർ
    0.07
     Provided
    0.07
     സര്
    0.07
     claramente
    0.07
    Activations Density 0.020%

    No Known Activations