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. 44139
    Prev
    Next
    INDEX
    Explanations

    a

    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
     കോടത
    -0.09
     forwards
    -0.08
     بنیاد
    -0.08
    hetics
    -0.08
     foundation
    -0.08
     Foundations
    -0.08
     Gaeilge
    -0.07
     schilder
    -0.07
    _FORWARD
    -0.07
    遂
    -0.07
    POSITIVE LOGITS
     inactive
    0.13
    inactive
    0.12
     initially
    0.12
    Initially
    0.12
    Inactive
    0.12
     Initially
    0.11
    Deactivate
    0.11
     dormant
    0.11
    .hide
    0.11
     inhibits
    0.10
    Activations Density 0.004%

    No Known Activations