Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43224
    Prev
    Next
    INDEX
    Explanations

    +

    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
    担
    -0.08
     staffing
    -0.08
    转换
    -0.07
     canonical
    -0.07
     pollen
    -0.07
    脸
    -0.07
    (EFFECT
    -0.07
     muiden
    -0.07
     commissioning
    -0.07
     pase
    -0.07
    POSITIVE LOGITS
     Müller
    0.08
    _require
    0.08
    Inbox
    0.07
    યોગ
    0.07
     ayam
    0.07
     accomp
    0.07
    ождении
    0.07
     antwoord
    0.07
     আন্দ
    0.07
     пог
    0.07
    Activations Density 0.010%

    No Known Activations