© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48897
    Prev
    Next
    INDEX
    Explanations

    práct

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Members
    -0.08
     Elements
    -0.08
    serialization
    -0.08
     раст
    -0.07
     Serializable
    -0.07
    .codegen
    -0.07
    Ｐ
    -0.07
    ांच
    -0.07
     juice
    -0.07
     POSITION
    -0.07
    POSITIVE LOGITS
    amo
    0.10
    �
    0.08
    ím
    0.08
    ystem
    0.08
    -------------
    0.08
    hf
    0.08
     pathogen
    0.08
    zki
    0.08
     جهان
    0.07
    ique
    0.07
    Activations Density 0.001%

    No Known Activations