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

    Neuronpedia

    APICircuit 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. 7-RESID-POST-AA
    6. 131011
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     δι
    -0.08
     comeback
    -0.08
    IFA
    -0.08
    Diam
    -0.08
    Fluid
    -0.08
     INS
    -0.07
     ослож
    -0.07
     MEM
    -0.07
    blocks
    -0.07
    Factories
    -0.07
    POSITIVE LOGITS
    liness
    0.08
     Spar
    0.08
    ahas
    0.08
     şekl
    0.07
    라는
    0.07
    ашта
    0.07
     Ober
    0.07
     kyn
    0.07
    ๆ
    0.07
     spel
    0.07
    Activations Density 0.030%

    No Known Activations