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. 112662
    Prev
    Next
    INDEX
    Explanations

    certificate

    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
    🏻
    -0.08
    🏼
    -0.08
     leden
    -0.07
    żą
    -0.07
    Cue
    -0.07
     Ved
    -0.07
    hy
    -0.07
    eight
    -0.07
     đây
    -0.07
    week
    -0.07
    POSITIVE LOGITS
    ificates
    0.11
    体系
    0.09
    /lic
    0.09
    IFICATE
    0.08
    서를
    0.08
    制度
    0.08
    /license
    0.08
     жай
    0.08
     czego
    0.07
    �
    0.07
    Activations Density 0.014%

    No Known Activations