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. 275
    Prev
    Next
    INDEX
    Explanations

    linear algebra

    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
     combustible
    -0.08
     �
    -0.08
     editions
    -0.08
     �
    -0.08
     из
    -0.08
     �
    -0.08
     ಧ
    -0.08
     �
    -0.08
     xây
    -0.07
     sensational
    -0.07
    POSITIVE LOGITS
    vector
    0.11
    vectors
    0.11
     Vec
    0.10
     vector
    0.10
     vectors
    0.09
    	vector
    0.09
     vetor
    0.09
    Vectors
    0.09
    -vector
    0.09
    <vector
    0.08
    Activations Density 0.011%

    No Known Activations