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. 54083
    Prev
    Next
    INDEX
    Explanations

    ional

    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
     porcelain
    -0.08
     تقريب
    -0.08
     отношения
    -0.08
    ENV
    -0.07
     уч
    -0.07
     Oceans
    -0.07
    ойн
    -0.07
    charge
    -0.07
     ci
    -0.07
    Lov
    -0.07
    POSITIVE LOGITS
     glimps
    0.10
    씩
    0.10
     бывает
    0.09
     standout
    0.09
     бывают
    0.09
     unnoticed
    0.08
     slipped
    0.08
     stumbling
    0.08
    ına
    0.08
     bursts
    0.08
    Activations Density 0.014%

    No Known Activations