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. 65148
    Prev
    Next
    INDEX
    Explanations

    void

    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
     unlimited
    -0.07
     kuten
    -0.07
    િતા
    -0.07
     proceso
    -0.07
     flourish
    -0.07
     prioridades
    -0.07
    נתי
    -0.07
    cuento
    -0.07
    kunst
    -0.07
    িত
    -0.07
    POSITIVE LOGITS
     dejado
    0.09
     сразу
    0.09
     removed
    0.09
     лидер
    0.09
     destabil
    0.09
     dejó
    0.08
     влияние
    0.08
    _removed
    0.08
     потер
    0.08
    Leadership
    0.08
    Activations Density 0.030%

    No Known Activations