© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 97328
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    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
     striving
    -0.10
     embracing
    -0.10
     لض
    -0.10
    ※
    -0.09
     strives
    -0.09
     endeavors
    -0.09
     स्वीकार
    -0.09
     contemplation
    -0.09
    Choosing
    -0.09
     тщ
    -0.09
    POSITIVE LOGITS
     give
    0.21
     tell
    0.21
     Tell
    0.20
    Tell
    0.19
    tell
    0.18
    Give
    0.18
    give
    0.17
     Give
    0.17
    Show
    0.17
     show
    0.17
    Activations Density 0.064%

    No Known Activations