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. 65256
    Prev
    Next
    INDEX
    Explanations

    product

    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
    $count
    -0.09
     apă
    -0.09
    াফ
    -0.08
    افي
    -0.08
     soli
    -0.08
    $self
    -0.07
     Gujarat
    -0.07
    ाफ
    -0.07
     vulnerable
    -0.07
    処
    -0.07
    POSITIVE LOGITS
    -rest
    0.08
     будущ
    0.08
     будет
    0.08
     앞으로
    0.08
    _controller
    0.07
     Auftrag
    0.07
    (rest
    0.07
     уведом
    0.07
     лест
    0.07
     конечно
    0.07
    Activations Density 0.004%

    No Known Activations