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. 53060
    Prev
    Next
    INDEX
    Explanations

    mountains and peaks

    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
     polymer
    -0.09
     trusting
    -0.08
     письмо
    -0.08
     이메일
    -0.08
     imediato
    -0.08
     prophyl
    -0.08
     antiviral
    -0.08
     эксперимент
    -0.08
     polyurethane
    -0.08
     plastics
    -0.08
    POSITIVE LOGITS
     पर्व
    0.14
     volcano
    0.12
     towering
    0.11
     mountains
    0.11
     tallest
    0.11
    顶部
    0.11
     Volcano
    0.11
     mountain
    0.10
     volcan
    0.10
     Mountains
    0.10
    Activations Density 0.027%

    No Known Activations