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. 52942
    Prev
    Next
    INDEX
    Explanations

    init

    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
    ­d
    -0.08
     almak
    -0.07
     вос
    -0.07
    -'.$
    -0.07
    hangi
    -0.07
    ордин
    -0.07
     mécanique
    -0.07
    事情
    -0.07
    _PAIR
    -0.07
     Ivan
    -0.07
    POSITIVE LOGITS
     estratég
    0.08
     пас
    0.07
     Lia
    0.07
     chaleure
    0.07
    rif
    0.07
    �
    0.07
    .Collectors
    0.07
     pene
    0.07
    pliers
    0.07
     еш
    0.07
    Activations Density 0.001%

    No Known Activations