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. 114106
    Prev
    Next
    INDEX
    Explanations

    outdated things in houses

    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
     awaits
    -0.09
     Voraussetzung
    -0.09
    Configurer
    -0.09
     pà
    -0.08
    ì
    -0.08
    {↵
    -0.08
    alana
    -0.08
    μ
    -0.08
     IMessage
    -0.07
    ៀ
    -0.07
    POSITIVE LOGITS
    老
    0.12
     outdated
    0.11
     oldest
    0.11
     aging
    0.11
     പഴ
    0.11
     eldre
    0.11
     older
    0.11
    Older
    0.10
    旧
    0.10
     vintage
    0.10
    Activations Density 0.046%

    No Known Activations