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. 60553
    Prev
    Next
    INDEX
    Explanations

    complete graph

    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
     rewind
    -0.09
     gan
    -0.08
     placer
    -0.08
     Sonne
    -0.08
     Bowman
    -0.07
     pleasure
    -0.07
     lys
    -0.07
     expertise
    -0.07
     geprägt
    -0.07
     فضل
    -0.07
    POSITIVE LOGITS
    minus
    0.08
     (!)
    0.08
    Functor
    0.08
    Tournament
    0.08
    nop
    0.08
     demonstra
    0.08
    012
    0.08
    宴
    0.07
    wire
    0.07
    Fest
    0.07
    Activations Density 0.004%

    No Known Activations