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. 58170
    Prev
    Next
    INDEX
    Explanations

    wickets

    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
    旭
    -0.08
    金
    -0.08
     gold
    -0.07
    会议
    -0.07
    -film
    -0.07
    τέ
    -0.07
     Overall
    -0.07
     Gold
    -0.07
    )..
    -0.07
     mini
    -0.07
    POSITIVE LOGITS
     muscul
    0.08
     conservação
    0.08
     самым
    0.08
    არო
    0.08
     consument
    0.07
     conservar
    0.07
     cilind
    0.07
    റണ
    0.07
    ाऱ्या
    0.07
     conserving
    0.07
    Activations Density 0.001%

    No Known Activations