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. 58445
    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
    �
    -0.08
    (as
    -0.08
    batch
    -0.07
    -0.07
    flo
    -0.07
    759
    -0.07
    Beam
    -0.07
    758
    -0.07
     omfatt
    -0.07
    (['/
    -0.07
    POSITIVE LOGITS
     interrog
    0.08
     bloody
    0.08
     Escol
    0.08
    تا
    0.08
    თა
    0.08
     gebru
    0.08
     帝
    0.08
    жьы
    0.08
     Embed
    0.08
     Tue
    0.08
    Activations Density 0.006%

    No Known Activations