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. 9205
    Prev
    Next
    INDEX
    Explanations

    opposite values/numbers

    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
    etop
    -0.08
    Fil
    -0.08
     témoign
    -0.08
     തട
    -0.07
     histoire
    -0.07
     infiltr
    -0.07
    enabled
    -0.07
     infiltration
    -0.07
    .enabled
    -0.07
     diá
    -0.07
    POSITIVE LOGITS
     求
    0.09
     conjug
    0.09
     mates
    0.09
    求
    0.09
    คือ
    0.09
    �
    0.09
     spouse
    0.08
    ाधिकारी
    0.08
     Schwester
    0.08
     opposite
    0.08
    Activations Density 0.052%

    No Known Activations