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. 113802
    Prev
    Next
    INDEX
    Explanations

    still life art

    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
     agrad
    -0.09
     sonuç
    -0.08
    (~
    -0.08
     Throughout
    -0.08
     cevap
    -0.08
    GROUP
    -0.08
     kus
    -0.08
    riy
    -0.08
     throughout
    -0.07
    .manage
    -0.07
    POSITIVE LOGITS
    描
    0.14
     depicting
    0.13
     depicted
    0.11
     depict
    0.11
     faithfully
    0.11
     depicts
    0.10
     depiction
    0.10
     watercolor
    0.10
     scènes
    0.10
     escena
    0.10
    Activations Density 0.096%

    No Known Activations