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. 45135
    Prev
    Next
    INDEX
    Explanations

    Code and references

    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
    inux
    -0.08
     acidic
    -0.08
    aton
    -0.07
    ура
    -0.07
    axi
    -0.07
     DWORD
    -0.07
    ाइन
    -0.07
    ाब
    -0.07
     stre
    -0.07
    ítico
    -0.07
    POSITIVE LOGITS
    按摩
    0.09
    assion
    0.08
    alyze
    0.08
    divider
    0.08
    Vak
    0.07
    ijf
    0.07
     Wandel
    0.07
    painting
    0.07
    _some
    0.07
     analyze
    0.07
    Activations Density 0.000%

    No Known Activations