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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2490
    Prev
    Next
    INDEX
    Explanations

    ment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nu
    -0.07
     entr
    -0.07
    niku
    -0.07
     intra
    -0.07
    Так
    -0.07
     Meadows
    -0.07
     Verse
    -0.07
    -0.07
    款
    -0.07
    -0.07
    POSITIVE LOGITS
     financed
    0.08
    type
    0.08
    ಿಂದ
    0.08
     slip
    0.08
     furnish
    0.07
     Eg
    0.07
    atoi
    0.07
     furnished
    0.07
     NSA
    0.07
     мог
    0.07
    Activations Density 0.032%

    No Known Activations