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. 3-RESID-POST-AA
    6. 12242
    Prev
    Next
    INDEX
    Explanations

    traveled

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     repr
    -0.09
    Vit
    -0.08
     Vit
    -0.08
    VAC
    -0.08
     adjustments
    -0.08
    trad
    -0.08
    plain
    -0.08
    VF
    -0.08
    Changer
    -0.07
     Cav
    -0.07
    POSITIVE LOGITS
     tam
    0.08
    多少
    0.07
     eyebrow
    0.07
    �
    0.07
     proximal
    0.07
     dichos
    0.07
     pursuant
    0.07
     medd
    0.07
    ว
    0.07
    娘
    0.07
    Activations Density 0.089%

    No Known Activations