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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 120297
    Prev
    Next
    INDEX
    Explanations

    bedrooms

    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
     Tob
    -0.08
    .Invocation
    -0.08
     feb
    -0.07
    icks
    -0.07
    itures
    -0.07
    ]&
    -0.07
    .Mod
    -0.07
    െട
    -0.07
     Polly
    -0.07
    Tur
    -0.07
    POSITIVE LOGITS
     hospitais
    0.09
    ording
    0.08
     worlds
    0.08
     entschieden
    0.08
    Bere
    0.08
    dde
    0.08
    ตำ
    0.08
     cuffs
    0.08
    ادت
    0.08
     MUSIC
    0.08
    Activations Density 0.002%

    No Known Activations