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. 11576
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    Ladies
    -0.08
    Bathroom
    -0.08
    Highlighted
    -0.08
     mistaken
    -0.08
    dream
    -0.07
    것
    -0.07
     accru
    -0.07
     بالخ
    -0.07
     inducing
    -0.07
    POSITIVE LOGITS
    .new
    0.10
    .randn
    0.09
    .arange
    0.09
    .makedirs
    0.09
    .send
    0.09
    ::
    0.09
    .some
    0.09
    .signal
    0.09
     Viktor
    0.08
    .text
    0.08
    Activations Density 0.035%

    No Known Activations