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. 44269
    Prev
    Next
    INDEX
    Explanations

    vocabulary

    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
    projekt
    -0.08
     responsables
    -0.08
     zonne
    -0.08
    线路
    -0.08
     visibles
    -0.08
     Linien
    -0.08
    /frontend
    -0.08
     переход
    -0.08
     realizadas
    -0.08
     responsable
    -0.08
    POSITIVE LOGITS
     শব্দ
    0.11
     unfamiliar
    0.11
     શબ્દ
    0.11
     शब्द
    0.11
     معنی
    0.11
     vocabulary
    0.10
     palavra
    0.10
     բառ
    0.10
     synonyms
    0.10
    词
    0.10
    Activations Density 0.070%

    No Known Activations