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. 44991
    Prev
    Next
    INDEX
    Explanations

    positive

    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
     Tatsache
    -0.08
    �
    -0.08
    asit
    -0.07
    .fit
    -0.07
    ിട്ട
    -0.07
    meet
    -0.07
     gemacht
    -0.07
    .swift
    -0.07
     Appointment
    -0.07
    bü
    -0.07
    POSITIVE LOGITS
     방향
    0.10
    쪽
    0.10
    方向
    0.09
     direction
    0.08
     direção
    0.08
    轴
    0.08
    tow
    0.08
    沿
    0.08
     напрям
    0.08
     longitude
    0.08
    Activations Density 0.010%

    No Known Activations