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. 42057
    Prev
    Next
    INDEX
    Explanations

    Research paper references

    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
    Trust
    -0.11
     Trust
    -0.10
    trust
    -0.10
     Dare
    -0.09
     brownies
    -0.09
     trust
    -0.08
    整改
    -0.08
     modifica
    -0.08
     jogging
    -0.08
    润
    -0.08
    POSITIVE LOGITS
     stereotyp
    0.09
     repetitive
    0.08
     repetition
    0.08
     centrifugal
    0.07
     적
    0.07
     Copier
    0.07
     laser
    0.07
    411
    0.07
     optic
    0.07
    iog
    0.07
    Activations Density 0.002%

    No Known Activations