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. 67735
    Prev
    Next
    INDEX
    Explanations

    Space filaments

    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
     nut
    -0.08
     обрат
    -0.08
     plum
    -0.07
    stab
    -0.07
    nard
    -0.07
    Objectives
    -0.07
    Digits
    -0.07
    gear
    -0.07
    Render
    -0.07
    riv
    -0.07
    POSITIVE LOGITS
     clustered
    0.10
     clustering
    0.10
     Cluster
    0.09
     clusters
    0.09
     شبكة
    0.09
     highways
    0.09
     Arabs
    0.09
     MULT
    0.09
    Cluster
    0.08
    	cluster
    0.08
    Activations Density 0.002%

    No Known Activations