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. 23-RESID-POST-AA
    6. 97070
    Prev
    Next
    INDEX
    Explanations

    Dates and space race

    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
     vortex
    -0.09
    .jupiter
    -0.07
     vort
    -0.07
    τά
    -0.07
     cybersecurity
    -0.07
     ransomware
    -0.07
    TPS
    -0.07
     Mosk
    -0.07
    েটে
    -0.07
     Jin
    -0.07
    POSITIVE LOGITS
     nullable
    0.10
     Foreign
    0.10
     foreign
    0.09
    Foreign
    0.09
     lending
    0.09
     विदेशी
    0.09
    .Foreign
    0.09
     étrang
    0.08
     విద
    0.08
     laag
    0.08
    Activations Density 0.001%

    No Known Activations