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. 98206
    Prev
    Next
    INDEX
    Explanations

    reptiles

    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
     peanuts
    -0.08
     boleto
    -0.08
     أور
    -0.08
    btc
    -0.08
     ماي
    -0.08
     Pois
    -0.08
    投注
    -0.08
     বিন
    -0.08
     curs
    -0.07
    .radius
    -0.07
    POSITIVE LOGITS
     reptiles
    0.15
     agama
    0.14
     agam
    0.14
     rept
    0.13
     monitor
    0.13
     l
    0.13
     Monitor
    0.12
     Gecko
    0.12
     monitors
    0.12
    Monitor
    0.12
    Activations Density 0.010%

    No Known Activations