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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45100
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     relata
    -0.08
     hann
    -0.08
     birlikte
    -0.08
    రం
    -0.07
     kaikki
    -0.07
    orpen
    -0.07
    306
    -0.07
    wag
    -0.07
    isd
    -0.07
     everywhere
    -0.07
    POSITIVE LOGITS
     หรือ
    0.13
     oppure
    0.12
    하거나
    0.12
     কিংবা
    0.11
     또는
    0.11
     ataupun
    0.11
     아니
    0.11
     அல்லது
    0.11
    たり
    0.11
     либо
    0.10
    Activations Density 0.155%

    No Known Activations