© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 6473
    Prev
    Next
    INDEX
    Explanations

    ing

    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
    duced
    -0.08
     thin
    -0.07
    ased
    -0.07
    ANTE
    -0.07
    ANTES
    -0.07
     γίνεται
    -0.07
    istoire
    -0.07
     دهید
    -0.07
    aderos
    -0.07
    ATIO
    -0.07
    POSITIVE LOGITS
    ency
    0.27
    encies
    0.27
    ENCY
    0.19
    encji
    0.16
    encie
    0.16
    ência
    0.15
    encias
    0.14
    ências
    0.13
    enciamento
    0.13
    enc
    0.13
    Activations Density 0.002%

    No Known Activations