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. 12684
    Prev
    Next
    INDEX
    Explanations

    height

    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
    �
    -0.09
    ankind
    -0.08
     έτσι
    -0.08
     Sands
    -0.08
     Chandler
    -0.08
     Matem
    -0.08
     Wharf
    -0.08
    ängen
    -0.08
     Adler
    -0.08
     sands
    -0.08
    POSITIVE LOGITS
    471
    0.09
     sprintf
    0.08
     lettering
    0.07
    etera
    0.07
     sexual
    0.07
    468
    0.07
     ஆகிய
    0.07
    Impact
    0.07
    469
    0.07
     ves
    0.07
    Activations Density 0.006%

    No Known Activations