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. 347
    Prev
    Next
    INDEX
    Explanations

    sorting algorithms

    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
    aumont
    -0.09
     penchant
    -0.09
     motives
    -0.08
    Would
    -0.08
    ামে
    -0.08
    ирад
    -0.08
    inseng
    -0.08
    անն
    -0.08
    _taken
    -0.08
     costat
    -0.08
    POSITIVE LOGITS
     hinter
    0.09
    .ini
    0.08
     shattered
    0.08
     иг
    0.07
     Fung
    0.07
    Cfg
    0.07
     инфраструкт
    0.07
    最高
    0.07
     Rune
    0.07
     microp
    0.07
    Activations Density 0.001%

    No Known Activations