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. 49392
    Prev
    Next
    INDEX
    Explanations

    need

    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
     pulley
    -0.09
     Perez
    -0.08
    BDC
    -0.08
    TMP
    -0.08
    feb
    -0.08
    freeze
    -0.08
     quadru
    -0.08
    Dll
    -0.08
    avar
    -0.07
    ópolis
    -0.07
    POSITIVE LOGITS
      ↵
    0.09
     conversational
    0.09
     requested
    0.08
     advising
    0.08
     prescribing
    0.08
    (↵
    0.08
     chodzi
    0.08
     articulate
    0.08
     argumentative
    0.08
     предостав
    0.07
    Activations Density 0.036%

    No Known Activations