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. 60542
    Prev
    Next
    INDEX
    Explanations

    4

    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
    ूर्ण
    -0.08
     adecu
    -0.08
     नेत
    -0.08
     indicators
    -0.08
    重点
    -0.07
    准确
    -0.07
    劲
    -0.07
    तः
    -0.07
     encarg
    -0.07
     komun
    -0.07
    POSITIVE LOGITS
    *-
    0.08
    viol
    0.08
    .Typed
    0.07
    .loc
    0.07
    'U
    0.07
     incarnation
    0.07
    Hist
    0.07
    .cell
    0.07
    �
    0.07
    utt
    0.07
    Activations Density 0.001%

    No Known Activations