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. 113783
    Prev
    Next
    INDEX
    Explanations

    =

    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
    dej
    -0.08
    Pig
    -0.08
    弊
    -0.07
     склон
    -0.07
     domanda
    -0.07
    ioso
    -0.07
    Nep
    -0.07
    Pile
    -0.07
    క
    -0.07
    _prob
    -0.07
    POSITIVE LOGITS
     Aurora
    0.09
    -hidden
    0.08
    ↵///
    0.08
     тру
    0.07
    ↵//
    0.07
    last
    0.07
     Hers
    0.07
    …,
    0.07
     honey
    0.07
     RN
    0.07
    Activations Density 0.019%

    No Known Activations